diff --git a/docs/source/conf.py b/docs/source/conf.py
index 4931e0c7..e40fb0d7 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -41,6 +41,7 @@
     "sphinx_rtd_theme",
     "nbsphinx",
     "sphinx.ext.mathjax",
+    "sphinxcontrib.youtube",
 ]
 
 templates_path = ["_templates"]
@@ -234,7 +235,6 @@ def generate_index(self, index_path, file_paths, dir_paths, source_dir):
             f.write(lines)
 
     def generate_autodoc(self, doc_path, source_file):
-
         # Make header
         short_name = source_file.name.replace(".py", "")
         lines = ""
diff --git a/docs/source/index.rst b/docs/source/index.rst
index 1725e118..5f27b7b9 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -31,6 +31,8 @@ for working with these environments.
 A whitepaper on the design philosophy behind BSK-RL and an example use case can be 
 :download:`downloaded here <_static/stephenson_bskrl_2024.pdf>`.
 
+..  youtube:: 8qR-AGrCFQw
+
 Quickstart
 ----------
 Installation
diff --git a/docs/source/release_notes.rst b/docs/source/release_notes.rst
index 0b11ce97..c914fab8 100644
--- a/docs/source/release_notes.rst
+++ b/docs/source/release_notes.rst
@@ -26,7 +26,8 @@ Development Version
 * Improve performance of :class:`~bsk_rl.obs.Eclipse` observations by about 95%.
 * Logs a warning if the initial battery charge or buffer level is incompatible with its capacity.
 * Optimize communication when all satellites are communicating with each other.
-
+* Enable Vizard visualization of the environment by setting the ``vizard_dir`` and ``vizard_settings``
+  options in the environment.
 
 
 Version 1.0.1
diff --git a/examples/continuous_orbit_manuevers.ipynb b/examples/continuous_orbit_manuevers.ipynb
new file mode 100644
index 00000000..a733910b
--- /dev/null
+++ b/examples/continuous_orbit_manuevers.ipynb
@@ -0,0 +1,464 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Getting Started\n",
+    "This tutorial demonstrates the configuration and use of a simple BSK-RL environment.\n",
+    "BSK-RL and dependencies should already be installed at this point (see [Installation](../install.rst)\n",
+    "if you haven't installed the package yet).\n",
+    "\n",
+    "## Load Modules\n",
+    "In this tutorial, the environment will be created with `gym.make`, so it is necessary to\n",
+    "import the top-level `bsk_rl` module as well as `gym` and `bsk_rl` components."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %matplotlib qt  # Uncomment to use interactive plotting, may need `pip install PyQt5`\n",
+    "\n",
+    "import numpy as np\n",
+    "from functools import partial\n",
+    "from bsk_rl import act, obs, sats, ConstellationTasking, comm\n",
+    "from bsk_rl.sim import dyn, fsw\n",
+    "from bsk_rl.utils.orbital import relative_to_chief, random_orbit, random_unit_vector\n",
+    "from bsk_rl.scene import FibonacciSphereRSOPoints\n",
+    "from bsk_rl.data import RSOInspectionReward, FuelPenalty\n",
+    "\n",
+    "from Basilisk.architecture import bskLogging\n",
+    "from Basilisk.utilities.RigidBodyKinematics import MRP2C\n",
+    "\n",
+    "bskLogging.setDefaultLogLevel(bskLogging.BSK_WARNING)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If no errors were raised, you have a functional installation of `bsk_rl`.\n",
+    "\n",
+    "## Configure the Satellite\n",
+    "[Satellites](../api_reference/sats/index.rst) are configurable agents in the environment.\n",
+    "To make a new environment, start by specifying the [observations](../api_reference/obs/index.rst)\n",
+    "and [actions](../api_reference/act/index.rst) of a satellite type, as well as the underlying\n",
+    "Basilisk [simulation](../api_reference/sim/index.rst) models used by the satellite."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import types\n",
+    "\n",
+    "\n",
+    "class TumbleSat(sats.Satellite):\n",
+    "    observation_spec = [\n",
+    "        obs.SatProperties(dict(prop=\"r_BN_N\"), dict(prop=\"sigma_BN\")),\n",
+    "    ]\n",
+    "    action_spec = [act.Drift()]\n",
+    "    dyn_type = types.new_class(\"Dyn\", (dyn.ConjunctionDynModel, dyn.RSODynModel))\n",
+    "    fsw_type = fsw.BasicFSWModel\n",
+    "\n",
+    "\n",
+    "class ThrustSat(sats.Satellite):\n",
+    "    observation_spec = [\n",
+    "        obs.SatProperties(\n",
+    "            dict(prop=\"r_BN_N\"),\n",
+    "            dict(prop=\"c_hat_N\"),\n",
+    "            dict(prop=\"storage_level_fraction\"),\n",
+    "        ),\n",
+    "        obs.RelativeProperties(\n",
+    "            dict(prop=\"r_DC_N\"),\n",
+    "            chief_name=\"Tumbler\",\n",
+    "        ),\n",
+    "    ]\n",
+    "    action_spec = [act.MagicThrust(max_dv=100, fsw_action=\"action_inspect_rso\")]\n",
+    "    dyn_type = types.new_class(\"Dyn\", (dyn.ConjunctionDynModel, dyn.RSOImagingDynModel))\n",
+    "    fsw_type = types.new_class(\n",
+    "        \"FSW\",\n",
+    "        (\n",
+    "            fsw.SteeringFSWModel,\n",
+    "            fsw.MagicOrbitalManeuverFSWModel,\n",
+    "            fsw.RSOImagingFSWModel,\n",
+    "        ),\n",
+    "    )\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Making the Environment\n",
+    "For this example, we will be using the single-agent [SatelliteTasking](../api_reference/index.rst) \n",
+    "environment. Along with passing the satellite that we configured, the environment takes\n",
+    "a [scenario](../api_reference/scene/index.rst), which defines the environment the\n",
+    "satellite is acting in, and a [rewarder](../api_reference/data/index.rst), which defines\n",
+    "how data collected from the scenario is rewarded."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'Tumbler': Discrete(1),\n",
+       " 'Thrust-1': Box([-100. -100. -100.    0.], [100. 100. 100.  inf], (4,), float32),\n",
+       " 'Thrust-2': Box([-100. -100. -100.    0.], [100. 100. 100.  inf], (4,), float32)}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "scanner_sat_args = dict(\n",
+    "    imageAttErrorRequirement=0.01,\n",
+    "    imageRateErrorRequirement=0.1,\n",
+    "    instrumentBaudRate=1,\n",
+    "    dataStorageCapacity=1e6,\n",
+    "    batteryStorageCapacity=1e9,\n",
+    "    storedCharge_Init=1e9,\n",
+    "    conjunction_radius=2.0,\n",
+    ")\n",
+    "\n",
+    "env = ConstellationTasking(\n",
+    "    satellites=[\n",
+    "        TumbleSat(\n",
+    "            \"Tumbler\",\n",
+    "            obs_type=dict,\n",
+    "            sat_args=dict(\n",
+    "                # sigma_init=np.zeros(3),\n",
+    "                omega_init=np.zeros(3),\n",
+    "                conjunction_radius=2.0,\n",
+    "            ),\n",
+    "        ),\n",
+    "        ThrustSat(\"Thrust-1\", obs_type=dict, sat_args=scanner_sat_args),\n",
+    "        ThrustSat(\"Thrust-2\", obs_type=dict, sat_args=scanner_sat_args),\n",
+    "    ],\n",
+    "    sat_arg_randomizer=relative_to_chief(\n",
+    "        chief_name=\"Tumbler\",\n",
+    "        chief_orbit=partial(random_orbit, i=0, Omega=0, omega=0, f=0),\n",
+    "        deputy_relative_state={\n",
+    "            \"Thrust-1\": lambda: np.concatenate(\n",
+    "                (random_unit_vector() * 50, np.zeros(3))\n",
+    "            ),\n",
+    "            \"Thrust-2\": np.array([-50, 0, 0, 0, 0, 0]),\n",
+    "        },\n",
+    "    ),\n",
+    "    scenario=FibonacciSphereRSOPoints(\n",
+    "        n_points=100,\n",
+    "        radius=1,\n",
+    "        theta_min=np.radians(30),\n",
+    "    ),\n",
+    "    # communicator=comm.LOSCommunication(),\n",
+    "    rewarder=(RSOInspectionReward(), FuelPenalty()),\n",
+    "    time_limit=5700.0 * 3,\n",
+    "    log_level=\"INFO\",\n",
+    ")\n",
+    "env.action_spaces"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Interacting with the Environment\n",
+    "\n",
+    "First, the environment is reset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[90;3m2024-12-26 11:31:30,574 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[mResetting environment with seed=624502672\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,771 \u001b[0m\u001b[36msats.satellite.Thrust-1.FSW    \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[m<Basilisk.architecture.messaging.NavTransMsgPayload.NavTransMsg_C; proxy of <Swig Object of type 'NavTransMsg_C *' at 0x34d2f8930> >\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,772 \u001b[0m\u001b[92msats.satellite.Thrust-2.FSW    \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[m<Basilisk.architecture.messaging.NavTransMsgPayload.NavTransMsg_C; proxy of <Swig Object of type 'NavTransMsg_C *' at 0x34d24bdb0> >\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,813 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[mEnvironment reset\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "observation, info = env.reset()  # seed=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, we take the scan action (`action=0`) a few times. This allows for the satellite to\n",
+    "settle its attitude in the nadir pointing mode to satisfy imaging conditions. Note that \n",
+    "the logs show little or no data accumulated in the first two steps as it settles, but\n",
+    "achieves 60 reward (corresponding to 60 seconds of imaging) by the third step."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[90;3m2024-12-26 11:31:30,818 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,819 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,819 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,820 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,821 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,821 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,821 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,822 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<0.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,917 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,918 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:30,992 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 8 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,067 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 10 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,068 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-1': 0.08, 'Thrust-2': 0.1}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,068 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[mTotal reward: {'Thrust-1': 0.08, 'Thrust-2': 0.1}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,068 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,069 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,069 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,071 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[mStep reward: {'Thrust-1': 0.08, 'Thrust-2': 0.1}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,071 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,072 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,072 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,073 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 1000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,073 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,074 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,074 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 1000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,074 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,174 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 1000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,174 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 1000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,250 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 9 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,327 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 9 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,328 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-1': 0.03, 'Thrust-2': 0.02}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,328 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[mFuelPenalty reward: {'Thrust-1': -0.010000000000005116, 'Thrust-2': -0.010000000000005116}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,329 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[mTotal reward: {'Thrust-1': 0.019999999999994883, 'Thrust-2': 0.009999999999994885}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,329 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,329 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,330 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,331 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[mStep reward: {'Thrust-1': 0.019999999999994883, 'Thrust-2': 0.009999999999994885}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,332 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,332 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,333 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,333 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 1500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,334 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,334 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,334 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 1500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,335 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,426 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 1500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,427 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 1500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,502 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 8 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,578 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 9 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,579 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-1': 0.02, 'Thrust-2': 0.03}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,579 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[mFuelPenalty reward: {'Thrust-1': -0.010000000000005116, 'Thrust-2': -0.010000000000005116}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,579 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[mTotal reward: {'Thrust-1': 0.009999999999994885, 'Thrust-2': 0.019999999999994883}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,580 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,580 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,580 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,582 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[mStep reward: {'Thrust-1': 0.009999999999994885, 'Thrust-2': 0.019999999999994883}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,583 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,584 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,584 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,584 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 2000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,585 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,585 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,586 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 2000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,586 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<1500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,672 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 2000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,672 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 2000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,746 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 7 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,820 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 9 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,820 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-1': 0.02, 'Thrust-2': 0.03}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,821 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[mTotal reward: {'Thrust-1': 0.02, 'Thrust-2': 0.03}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,821 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,821 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,822 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,823 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[mStep reward: {'Thrust-1': 0.02, 'Thrust-2': 0.03}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,824 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,824 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,824 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,825 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 2500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,825 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,826 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,826 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 2500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,826 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,969 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 2500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:31,969 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 2500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,041 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 10 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,113 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 10 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,114 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-1': 0.04, 'Thrust-2': 0.04}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,114 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[mFuelPenalty reward: {'Thrust-1': -0.010000000000005116, 'Thrust-2': -0.010000000000005116}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,114 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[mTotal reward: {'Thrust-1': 0.029999999999994885, 'Thrust-2': 0.029999999999994885}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,114 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,115 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,115 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,116 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[mStep reward: {'Thrust-1': 0.029999999999994885, 'Thrust-2': 0.029999999999994885}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,117 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,118 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,118 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,118 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 3000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,118 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,119 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,119 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 3000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,119 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<2500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,210 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 3000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,211 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 3000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,282 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 10 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,360 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 11 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,361 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-1': 0.04, 'Thrust-2': 0.04}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,361 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[mFuelPenalty reward: {'Thrust-1': -0.010000000000005116}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,361 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[mTotal reward: {'Thrust-1': 0.029999999999994885, 'Thrust-2': 0.04}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,362 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,362 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,362 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,364 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[mStep reward: {'Thrust-1': 0.029999999999994885, 'Thrust-2': 0.04}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,364 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,365 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,365 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,366 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 3500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,366 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,366 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,367 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 3500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,368 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,461 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 3500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,462 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 3500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,534 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 11 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,606 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 10 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,607 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-1': 0.02, 'Thrust-2': 0.03}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,607 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[mFuelPenalty reward: {'Thrust-1': -0.010000000000005116, 'Thrust-2': -0.010000000000005116}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,607 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[mTotal reward: {'Thrust-1': 0.009999999999994885, 'Thrust-2': 0.019999999999994883}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,608 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,608 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,608 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,610 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[mStep reward: {'Thrust-1': 0.009999999999994885, 'Thrust-2': 0.019999999999994883}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,611 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,611 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,611 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,612 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 4000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,612 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,613 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,613 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 4000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,614 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<3500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,708 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 4000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,709 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 4000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,781 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 11 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,853 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 10 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,854 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-2': 0.02}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,854 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[mTotal reward: {'Thrust-2': 0.02}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,854 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,855 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,855 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,856 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[mStep reward: {'Thrust-2': 0.02}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,857 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,858 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,858 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,859 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 4500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,859 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,860 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,860 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 4500.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,860 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,951 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 4500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:32,952 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 4500.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,024 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 13 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,097 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 10 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,098 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-1': 0.01, 'Thrust-2': 0.01}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,098 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[mFuelPenalty reward: {'Thrust-2': -0.010000000000005116}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,099 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[mTotal reward: {'Thrust-1': 0.01, 'Thrust-2': -5.115699530655604e-15}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,099 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,099 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,099 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,101 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[mStep reward: {'Thrust-1': 0.01, 'Thrust-2': -5.115699530655604e-15}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,102 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[93;1m=== STARTING STEP ===\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,102 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[93mWARNING    \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[93mRequires retasking but received no task.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,102 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mThrusting with inertial dV [0. 0. 0.] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,103 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[msetting timed terminal event at 5000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,103 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,104 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mThrusting with inertial dV [0.01 0.   0.  ] with 500.0 second drift.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,104 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[msetting timed terminal event at 5000.0\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,105 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<4500.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mFSW action action_inspect_rso activated.\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,194 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mtimed termination at 5000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,195 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mtimed termination at 5000.0 \u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,267 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mInspected 10 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,339 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mInspected 12 points this step\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,340 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[mRSOInspectionReward reward: {'Thrust-2': 0.01}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,340 \u001b[0m\u001b[mdata.composition               \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[mFuelPenalty reward: {'Thrust-2': -0.010000000000005116}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,340 \u001b[0m\u001b[mdata.base                      \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[mTotal reward: {'Thrust-2': -5.115699530655604e-15}\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,341 \u001b[0m\u001b[34msats.satellite.Tumbler         \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[34mTumbler: \u001b[0m\u001b[mSatellite Tumbler requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,341 \u001b[0m\u001b[36msats.satellite.Thrust-1        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[36mThrust-1: \u001b[0m\u001b[mSatellite Thrust-1 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,341 \u001b[0m\u001b[92msats.satellite.Thrust-2        \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[92mThrust-2: \u001b[0m\u001b[mSatellite Thrust-2 requires retasking\u001b[0m\n",
+      "\u001b[90;3m2024-12-26 11:31:33,343 \u001b[0m\u001b[mgym                            \u001b[0m\u001b[mINFO       \u001b[0m\u001b[33m<5000.00> \u001b[0m\u001b[mStep reward: {'Thrust-2': -5.115699530655604e-15}\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "for _ in range(10):\n",
+    "    actions = {\n",
+    "        \"Thrust-1\": np.array([0.01 * np.round(np.random.rand()), 0, 0, 500]),\n",
+    "        \"Thrust-2\": np.array([0.01 * np.round(np.random.rand()), 0, 0, 500]),\n",
+    "    }\n",
+    "    # for sat in env.satellites:\n",
+    "    #     if sat.requires_retasking:\n",
+    "    #         if isinstance(sat, TumbleSat):\n",
+    "    #             actions[sat.name] = 0\n",
+    "    #         else:\n",
+    "    #             actions[sat.name] = np.concatenate(\n",
+    "    #                 (np.random.uniform(-20, 20, 3), np.random.uniform(0, 200, 1))\n",
+    "    #             )\n",
+    "\n",
+    "    observation, reward, terminated, truncated, info = env.step(actions)\n",
+    "\n",
+    "    # print(env.satellites[1].data_store.data.point_inspect_status)\n",
+    "    # print(\"storage:\", observation[\"Thrust-1\"][\"sat_props\"][\"storage_level_fraction\"])\n",
+    "\n",
+    "# BN = MRP2C(observation[\"Tumbler\"][\"sat_props\"][\"sigma_BN\"])\n",
+    "\n",
+    "# fig, ax = plt.subplots(1, 1, subplot_kw=dict(projection=\"3d\"))\n",
+    "# for point, inspected in env.satellites[1].data_store.data.point_inspect_status.items():\n",
+    "#     ax.scatter(*(BN.T @ point.r_PB_B), color=\"tab:green\" if inspected else \"tab:red\")\n",
+    "\n",
+    "# # ax.scatter(\n",
+    "# #     *observation[\"Thrust-1\"][\"rel_props\"][\"r_DC_N\"], color=\"tab:blue\", marker=\"x\"\n",
+    "# # )\n",
+    "# ax.set_aspect(\"equal\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/pyproject.toml b/pyproject.toml
index 8d4b2989..2eda19ff 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -28,8 +28,8 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-docs = ["ipykernel", "ipywidgets", "nbdime", "nbsphinx", "sphinx-rtd-theme"]
-rllib = ["dm_tree", "pyarrow", "ray[rllib]", "scikit-image", "torch", "typer"]
+docs = ["ipykernel", "ipywidgets", "nbdime", "nbsphinx", "sphinx-rtd-theme", 'sphinxcontrib-youtube']
+rllib = ["dm_tree", "pyarrow", "ray[rllib]==2.35.0", "scikit-image", "torch", "typer"]
 
 [project.scripts]
 finish_install = "bsk_rl.finish_install:pck_install"
diff --git a/src/bsk_rl/act/__init__.py b/src/bsk_rl/act/__init__.py
index 6e49bec7..1240ec60 100644
--- a/src/bsk_rl/act/__init__.py
+++ b/src/bsk_rl/act/__init__.py
@@ -38,9 +38,25 @@ class MyActionSatellite(Satellite):
 +----------------------------+---------+-------------------------------------------------------------------------------------------------------+
 | :class:`Scan`              | 1       | Scan nadir, collecting data when pointing within a threshold.                                         |
 +----------------------------+---------+-------------------------------------------------------------------------------------------------------+
+
+Continuous Actions
+-------------------
+
+Use :class:`ContinuousAction` for actions with a continuous action space. Currently, satellites
+can only have a single continuous action in their ``action_spec``.
+
++----------------------------+-------------+-------------------------------------------------------------------------------------------------------+
+| **Action**                 |**Dimension**| **Description**                                                                                       |
++----------------------------+-------------+-------------------------------------------------------------------------------------------------------+
+| :class:`MagicThrust`       | 4           | Instantaneously change the satellite's velocity, and drift for some duration.                         |
++----------------------------+-------------+-------------------------------------------------------------------------------------------------------+
+
+
+
 """
 
 from bsk_rl.act.actions import Action
+from bsk_rl.act.continuous_action import ContinuousAction, MagicThrust
 from bsk_rl.act.discrete_actions import (
     Charge,
     Desat,
@@ -63,4 +79,6 @@ class MyActionSatellite(Satellite):
     "Downlink",
     "Image",
     "Scan",
+    "ContinuousAction",
+    "MagicThrust",
 ]
diff --git a/src/bsk_rl/act/actions.py b/src/bsk_rl/act/actions.py
index 8fd245c4..7ca5d73a 100644
--- a/src/bsk_rl/act/actions.py
+++ b/src/bsk_rl/act/actions.py
@@ -30,7 +30,6 @@ def select_action_builder(satellite: "Satellite") -> "ActionBuilder":
 
 
 class ActionBuilder(ABC):
-
     def __init__(self, satellite: "Satellite") -> None:
         """Base class for all action builders.
 
diff --git a/src/bsk_rl/act/continuous_action.py b/src/bsk_rl/act/continuous_action.py
new file mode 100644
index 00000000..74d1af6a
--- /dev/null
+++ b/src/bsk_rl/act/continuous_action.py
@@ -0,0 +1,133 @@
+"""Continuous actions set satellite behavior based on some continuous value."""
+
+import logging
+from abc import abstractmethod
+from typing import TYPE_CHECKING, Optional
+
+import numpy as np
+from gymnasium import spaces
+
+from bsk_rl.act.actions import Action, ActionBuilder
+
+if TYPE_CHECKING:  # pragma: no cover
+    from bsk_rl.sats import Satellite
+    from bsk_rl.scene.targets import Target
+
+logger = logging.getLogger(__name__)
+
+
+class ContinuousActionBuilder(ActionBuilder):
+    def __init__(self, satellite: "Satellite") -> None:
+        """Processes actions for a continuous action space.
+
+        Args:
+            satellite: Satellite to create actions for.
+        """
+        self.action_spec: list[ContinuousAction]
+        super().__init__(satellite)
+        assert len(self.action_spec) == 1, "Only one continuous action is supported."
+
+    @property
+    def _action(self) -> "ContinuousAction":
+        return self.action_spec[0]
+
+    @property
+    def action_space(self) -> spaces.Box:
+        """Continuous action space."""
+        return self._action.space
+
+    @property
+    def action_description(self) -> list[str]:
+        """Return a human-readable description of the continuous action space."""
+        return self._action.action_description()
+
+    def set_action(self, action: np.ndarray) -> None:
+        """Activate the action by setting the continuous value."""
+        self._action.set_action(action)
+
+
+class ContinuousAction(Action):
+    builder_type = ContinuousActionBuilder
+
+    def __init__(self, name: str = "discrete_act") -> None:
+        """Base class for discrete, integer-indexable actions.
+
+        Args:
+            name: Name of the action.
+        """
+        super().__init__(name=name)
+
+    @property
+    @abstractmethod
+    def space(self) -> spaces.Box:
+        """Return the action space."""
+        pass
+
+    @property
+    @abstractmethod
+    def action_description(self) -> list[str]:
+        """Return a description of the action space."""
+        pass
+
+    @abstractmethod
+    def set_action(self, action: np.ndarray) -> None:
+        """Activate an action by a continuous value."""
+        pass
+
+
+class MagicThrust(ContinuousAction):
+    # TODO set the fsw mode to carry out after action
+    def __init__(
+        self,
+        name: str = "thrust_act",
+        max_dv: float = float("inf"),
+        max_duration: float = float("inf"),
+        fsw_action: Optional[str] = None,
+    ) -> None:
+        """Instantaneously change the satellite's velocity, and drift for some duration.
+
+        TODO: Support specifying frame of thrust.
+
+        Args:
+            name: Name of the action.
+            max_dv: Maximum delta-V that can be applied. [m/s]
+        """
+        super().__init__(name)
+        self.max_dv = max_dv
+        self.max_duration = max_duration
+        self.fsw_action = fsw_action
+
+    @property
+    def space(self) -> spaces.Box:
+        """Return the action space."""
+        return spaces.Box(
+            low=np.array(
+                [-self.max_dv, -self.max_dv, -self.max_dv, self.simulator.sim_rate]
+            ),
+            high=np.array([self.max_dv, self.max_dv, self.max_dv, self.max_duration]),
+            shape=(4,),
+            dtype=np.float32,
+        )
+
+    @property
+    def action_description(self) -> list[str]:
+        """Description of the continuous action space."""
+        return ["dV_N_x", "dV_N_y", "dV_N_z", "duration"]
+
+    def set_action(self, action: np.ndarray) -> None:
+        """Thrust the satellite with a given inertial delta-V and drift for some duration."""
+        assert len(action) == 4, "Action must have 4 elements."
+        dv_N = action[0:3]
+        dt = action[3]
+
+        self.satellite.log_info(
+            f"Thrusting with inertial dV {dv_N} with {dt} second drift."
+        )
+        self.satellite.fsw.action_magic_thrust(dv_N)
+        self.satellite.update_timed_terminal_event(
+            self.satellite.simulator.sim_time + dt
+        )
+
+        # Activate the FSW action for the drift period
+        getattr(self.satellite.fsw, self.fsw_action)()
+        self.satellite.log_info(f"FSW action {self.fsw_action} activated.")
diff --git a/src/bsk_rl/data/__init__.py b/src/bsk_rl/data/__init__.py
index b86d2ab5..0195e6fd 100644
--- a/src/bsk_rl/data/__init__.py
+++ b/src/bsk_rl/data/__init__.py
@@ -74,11 +74,26 @@
         ...
     )
 
+Multiple reward systems can be added to the environment by instead passing an iterable of
+reward systems to the ``data`` field of the environment constructor:
+
+.. code-block:: python
+
+    env = ConstellationTasking(
+        ...,
+        data=(ScanningTimeReward(), SomeOtherReward()),
+        ...
+    )
+
+On the backend, this creates a :class:`~bsk_rl.data.composition.ComposedDataStore` that
+handles the combination of multiple reward systems.
 """
 
 from bsk_rl.data.base import GlobalReward
+from bsk_rl.data.fuel_penalty import FuelPenalty
 from bsk_rl.data.nadir_data import ScanningTimeReward
 from bsk_rl.data.no_data import NoReward
+from bsk_rl.data.rso_data import RSOInspectionReward
 from bsk_rl.data.unique_image_data import UniqueImageReward
 
 __doc_title__ = "Data & Reward"
@@ -87,4 +102,6 @@
     "NoReward",
     "UniqueImageReward",
     "ScanningTimeReward",
+    "RSOInspectionReward",
+    "FuelPenalty",
 ]
diff --git a/src/bsk_rl/data/base.py b/src/bsk_rl/data/base.py
index d9e9d609..d4986b0f 100644
--- a/src/bsk_rl/data/base.py
+++ b/src/bsk_rl/data/base.py
@@ -193,7 +193,7 @@ def reward(self, new_data_dict: dict[str, Data]) -> dict[str, float]:
             self.data += new_data
 
         nonzero_reward = {k: v for k, v in reward.items() if v != 0}
-        logger.info(f"Data reward: {nonzero_reward}")
+        logger.info(f"Total reward: {nonzero_reward}")
         return reward
 
 
diff --git a/src/bsk_rl/data/composition.py b/src/bsk_rl/data/composition.py
new file mode 100644
index 00000000..4f59bb73
--- /dev/null
+++ b/src/bsk_rl/data/composition.py
@@ -0,0 +1,236 @@
+"""Data composition classes."""
+
+import logging
+from typing import TYPE_CHECKING, Optional
+
+from bsk_rl.data.base import Data, DataStore, GlobalReward
+from bsk_rl.sats import Satellite
+from bsk_rl.scene.scenario import Scenario
+
+if TYPE_CHECKING:
+    from bsk_rl.sats import Satellite
+
+logger = logging.getLogger(__name__)
+
+
+class ComposedData(Data):
+    """Data for composed data types."""
+
+    def __init__(self, *data: Data) -> None:
+        """Data for composed data types.
+
+        Args:
+            data: Data types to compose.
+        """
+        self.data = data
+
+    def __add__(self, other: "ComposedData") -> "ComposedData":
+        """Combine two units of composed data.
+
+        Args:
+            other: Another unit of composed data to combine with this one.
+
+        Returns:
+            Combined unit of composed data.
+        """
+        if len(self.data) == 0 and len(other.data) == 0:
+            data = []
+        elif len(self.data) == 0:
+            data = [type(d)() + d for d in other.data]
+        elif len(other.data) == 0:
+            data = [d + type(d)() for d in self.data]
+        elif len(self.data) == len(other.data):
+            data = [d1 + d2 for d1, d2 in zip(self.data, other.data)]
+        else:
+            raise ValueError(
+                "ComposedData units must have the same number of data types."
+            )
+        return ComposedData(*data)
+
+    def __getattr__(self, name: str):
+        """Search for an attribute in the datas."""
+        for data in self.data:
+            if hasattr(data, name):
+                return getattr(data, name)
+        raise AttributeError(f"No Data in ComposedData has attribute '{name}'")
+
+
+class ComposedDataStore(DataStore):
+    data_type = ComposedData
+
+    def pass_data(self) -> None:
+        """Pass data to the sub-datastores.
+
+        :meta private:
+        """
+        for ds, data in zip(self.datastores, self.data.data):
+            ds.data = data
+
+    def __init__(
+        self,
+        satellite: "Satellite",
+        *datastore_types: type[DataStore],
+        initial_data: Optional[ComposedData] = None,
+    ):
+        """DataStore for composed data types.
+
+        Args:
+            satellite: Satellite which data is being stored for.
+            datastore_types: DataStore types to compose.
+            initial_data: Initial data to start the store with. Usually comes from
+                :class:`~bsk_rl.data.GlobalReward.initial_data`.
+        """
+        self.data: ComposedData
+        super().__init__(satellite, initial_data)
+        self.datastores = tuple([ds(satellite) for ds in datastore_types])
+        self.pass_data()
+
+    def __getattr__(self, name: str):
+        """Search for an attribute in the datastores."""
+        for datastore in self.datastores:
+            if hasattr(datastore, name):
+                return getattr(datastore, name)
+        raise AttributeError(
+            f"No DataStore in ComposedDataStore has attribute '{name}'"
+        )
+
+    def get_log_state(self) -> list:
+        """Pull information used in determining current data contribution."""
+        log_states = [ds.get_log_state() for ds in self.datastores]
+        return log_states
+
+    def compare_log_states(self, prev_state: list, new_state: list) -> Data:
+        """Generate a unit of composed data based on previous step and current step logs."""
+        data = [
+            ds.compare_log_states(prev, new)
+            for ds, prev, new in zip(self.datastores, prev_state, new_state)
+        ]
+        return ComposedData(*data)
+
+    def update_from_logs(self) -> Data:
+        """Update the data store based on collected information."""
+        new_data = super().update_from_logs()
+        self.pass_data()
+        return new_data
+
+    def update_with_communicated_data(self) -> None:
+        """Update the data store based on collected information from other satellites."""
+        super().update_with_communicated_data()
+        self.pass_data()
+
+
+class ComposedReward(GlobalReward):
+    datastore_type = ComposedDataStore
+
+    def pass_data(self) -> Data:
+        """Pass data to the sub-rewarders.
+
+        :meta private:
+        """
+        for rewarder, data in zip(self.rewarders, self.data.data):
+            rewarder.data = data
+
+    def __init__(self, *rewarders: GlobalReward) -> None:
+        """Rewarder for composed data types.
+
+        This type can be automatically constructed by passing a tuple of rewarders to
+        the environment constructor's `reward` argument.
+
+        Args:
+            rewarders: Global rewarders to compose.
+        """
+        super().__init__()
+        self.rewarders = rewarders
+
+    def __getattr__(self, name: str):
+        """Search for an attribute in the rewarders."""
+        for rewarder in self.rewarders:
+            if hasattr(rewarder, name):
+                return getattr(rewarder, name)
+        raise AttributeError(
+            f"No GlobalReward in ComposedReward has attribute '{name}'"
+        )
+
+    def reset_pre_sim_init(self) -> None:
+        """Handle resetting for all rewarders."""
+        super().reset_pre_sim_init()
+        for rewarder in self.rewarders:
+            rewarder.reset_pre_sim_init()
+
+    def reset_during_sim_init(self) -> None:
+        """Handle resetting for all rewarders."""
+        super().reset_during_sim_init()
+        for rewarder in self.rewarders:
+            rewarder.reset_during_sim_init()
+
+    def reset_post_sim_init(self) -> None:
+        """Handle resetting for all rewarders."""
+        super().reset_post_sim_init()
+        for rewarder in self.rewarders:
+            rewarder.reset_post_sim_init()
+
+    def reset_overwrite_previous(self) -> None:
+        """Handle resetting for all rewarders."""
+        super().reset_overwrite_previous()
+        for rewarder in self.rewarders:
+            rewarder.reset_overwrite_previous()
+
+    def link_scenario(self, scenario: Scenario) -> None:
+        """Link the rewarder to the scenario."""
+        super().link_scenario(scenario)
+        for rewarder in self.rewarders:
+            rewarder.link_scenario(scenario)
+
+    def initial_data(self, satellite: Satellite) -> ComposedData:
+        """Furnsish the datastore with :class:`ComposedData`."""
+        return ComposedData(
+            *[rewarder.initial_data(satellite) for rewarder in self.rewarders]
+        )
+
+    def create_data_store(self, satellite: Satellite) -> None:
+        """Create a :class:`CompositeDataStore` for a satellite."""
+        # TODO support passing kwargs
+        satellite.data_store = ComposedDataStore(
+            satellite,
+            *[r.datastore_type for r in self.rewarders],
+            initial_data=self.initial_data(satellite),
+        )
+        self.cum_reward[satellite.name] = 0.0
+        for rewarder in self.rewarders:
+            rewarder.cum_reward[satellite.name] = 0.0
+
+    def calculate_reward(
+        self, new_data_dict: dict[str, ComposedData]
+    ) -> dict[str, float]:
+        """Calculate reward for each data type and combine them."""
+        data_len = len(list(new_data_dict.values())[0].data)
+
+        for data in new_data_dict.values():
+            assert len(data.data) == data_len
+
+        reward = {}
+        if data_len != 0:
+            for i, rewarder in enumerate(self.rewarders):
+                reward_i = rewarder.calculate_reward(
+                    {sat_id: data.data[i] for sat_id, data in new_data_dict.items()}
+                )
+
+                # Logging
+                nonzero_reward = {k: v for k, v in reward_i.items() if v != 0}
+                if len(nonzero_reward) > 0:
+                    logger.info(f"{type(rewarder).__name__} reward: {nonzero_reward}")
+
+                for sat_id, sat_reward in reward_i.items():
+                    reward[sat_id] = reward.get(sat_id, 0.0) + sat_reward
+                    rewarder.cum_reward[sat_id] += sat_reward
+        return reward
+
+    def reward(self, new_data_dict: dict[str, ComposedData]) -> dict[str, float]:
+        """Return combined reward calculation and update data."""
+        reward = super().reward(new_data_dict)
+        self.pass_data()
+        return reward
+
+
+__doc_title__ = "Data Composition"
+__all__ = ["ComposedReward", "ComposedDataStore", "ComposedData"]
diff --git a/src/bsk_rl/data/fuel_penalty.py b/src/bsk_rl/data/fuel_penalty.py
new file mode 100644
index 00000000..ad04b193
--- /dev/null
+++ b/src/bsk_rl/data/fuel_penalty.py
@@ -0,0 +1,76 @@
+import logging
+from typing import TYPE_CHECKING, Callable, Optional
+
+import numpy as np
+
+from bsk_rl.data.base import Data, DataStore, GlobalReward
+
+if TYPE_CHECKING:
+    from bsk_rl.sats import Satellite
+    from bsk_rl.scene.targets import Target
+
+logger = logging.getLogger(__name__)
+
+
+class FuelData(Data):
+    """Data for fuel usage."""
+
+    def __init__(self, fuel_used: float = 0.0) -> None:
+        """Construct fuel data.
+
+        Args:
+            fuel_used: Amount of fuel used.
+        """
+        self.fuel_used = fuel_used
+
+    def __add__(self, other: "FuelData") -> "FuelData":
+        """Combine two units of fuel data.
+
+        Args:
+            other: Another unit of fuel data to combine with this one.
+
+        Returns:
+            Combined unit of fuel data.
+        """
+        fuel_used = self.fuel_used + other.fuel_used
+        return FuelData(fuel_used)
+
+
+class FuelDataStore(DataStore):
+    data_type = FuelData
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+    def get_log_state(self) -> float:
+        try:
+            return self.satellite.fsw.dv_available  # TODO update for other fuel models
+        except AttributeError:
+            return 0.0
+
+    def compare_log_states(self, prev_state: np.ndarray, new_state: np.ndarray) -> Data:
+        fuel_used = prev_state - new_state
+        return FuelData(fuel_used)
+
+
+class FuelPenalty(GlobalReward):
+    """Global penalty for fuel usage."""
+
+    datastore_type = FuelDataStore
+
+    def __init__(self, penalty_weight: float = 1.0) -> None:
+        """Construct fuel penalty.
+
+        Args:
+            penalty_weight: Scaling factor to apply to fuel penalty.
+        """
+        super().__init__()
+        self.penalty_weight = penalty_weight
+
+    def calculate_reward(self, new_data_dict: dict[str, FuelData]) -> dict[str, float]:
+        penalty = {
+            sat_name: -data.fuel_used * self.penalty_weight
+            for sat_name, data in new_data_dict.items()
+        }
+
+        return penalty
diff --git a/src/bsk_rl/data/rso_data.py b/src/bsk_rl/data/rso_data.py
new file mode 100644
index 00000000..c368d149
--- /dev/null
+++ b/src/bsk_rl/data/rso_data.py
@@ -0,0 +1,202 @@
+"""Data system for recording RSO surface."""
+
+import logging
+from typing import TYPE_CHECKING, Optional
+
+import numpy as np
+
+from bsk_rl.data.base import Data, DataStore, GlobalReward
+from bsk_rl.sats import Satellite
+from bsk_rl.scene.rso_points import RSOPoint
+from bsk_rl.sim.dyn import RSODynModel, RSOImagingDynModel
+from bsk_rl.utils import vizard
+
+if TYPE_CHECKING:
+    from bsk_rl.sats import Satellite
+
+logger = logging.getLogger(__name__)
+
+RSO = "rso"
+OBSERVER = "observer"
+
+
+class RSOInspectionData(Data):
+    def __init__(self, point_inspect_status: Optional[dict[RSOPoint, bool]] = None):
+        if point_inspect_status is None:
+            point_inspect_status = {}
+        self.point_inspect_status = point_inspect_status
+
+    def __add__(self, other: "RSOInspectionData"):
+        point_inspect_status = {}
+        point_inspect_status.update(self.point_inspect_status)
+        for point, access in other.point_inspect_status.items():
+            if point not in point_inspect_status:
+                point_inspect_status[point] = access
+            else:
+                point_inspect_status[point] = point_inspect_status[point] or access
+
+        return RSOInspectionData(point_inspect_status)
+
+
+class RSOInspectionDataStore(DataStore):
+    data_type = RSOInspectionData
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.point_access_recorders = []
+        self.storage_recorder = None
+
+        if issubclass(self.satellite.dyn_type, RSOImagingDynModel):
+            self.role = OBSERVER
+        else:
+            self.role = RSO
+
+    def set_storage_recorder(self, recorder):
+        self.storage_recorder = recorder
+        self.satellite.simulator.AddModelToTask(
+            self.satellite.dynamics.task_name, recorder, ModelPriority=1000
+        )
+
+    def add_point_access_recorder(self, recorder):
+        self.point_access_recorders.append(recorder)
+        self.satellite.simulator.AddModelToTask(
+            self.satellite.dynamics.task_name, recorder, ModelPriority=1000
+        )
+
+    def clear_recorders(self):
+        if self.storage_recorder:
+            self.storage_recorder.clear()
+        for recorder in self.point_access_recorders:
+            recorder.clear()
+
+    def get_log_state(self) -> list[list[bool]]:
+        """Log the storage unit state and point access state for all times in the step.
+
+        Returns:
+            todo
+        """
+        if self.role == RSO:
+            return None
+
+        log_len = len(self.storage_recorder.storageLevel)
+        if log_len <= 1:
+            imaging_req = np.zeros(log_len)
+        else:
+            imaging_req = np.diff(self.storage_recorder.storageLevel)
+            imaging_req = np.concatenate((imaging_req, [imaging_req[-1]]))
+
+        inspected_logs = []
+        for recorder in self.point_access_recorders:
+            inspected = np.logical_and(imaging_req, recorder.hasAccess)
+            inspected_logs.append(list(np.array(inspected)))
+
+        self.clear_recorders()
+
+        return inspected_logs
+
+    def compare_log_states(self, _, inspected_logs) -> Data:
+        if self.role == RSO:
+            return RSOInspectionData()
+
+        point_inspect_status = {}
+        for rso_point, log in zip(
+            self.data.point_inspect_status.keys(), inspected_logs
+        ):
+            if any(log):
+                point_inspect_status[rso_point] = True
+
+        self.update_point_colors(
+            [
+                rso_point
+                for rso_point in point_inspect_status
+                if point_inspect_status[rso_point]
+            ]
+        )
+
+        if len(point_inspect_status) > 0:
+            self.satellite.logger.info(
+                f"Inspected {len(point_inspect_status)} points this step"
+            )
+
+        return RSOInspectionData(point_inspect_status)
+
+    @vizard.visualize
+    def update_point_colors(self, rso_points, vizInstance=None, vizSupport=None):
+        """Update target colors in Vizard."""
+        for location in vizInstance.locations:
+            if location.stationName in [str(point) for point in rso_points]:
+                location.color = vizSupport.toRGBA255("tab:green", alpha=0.5)
+
+
+class RSOInspectionReward(GlobalReward):
+    datastore_type = RSOInspectionDataStore
+
+    def __init__(
+        self, inspection_reward_scale: float = 1.0, completion_bonus: float = 0.0
+    ):
+        super().__init__()
+        self.completion_bonus = completion_bonus
+        self.inspection_reward_scale = inspection_reward_scale
+
+    def reset_overwrite_previous(self) -> None:
+        super().reset_overwrite_previous()
+        self.bonus_reward_yielded = False
+
+    def reset_post_sim_init(self) -> None:
+        super().reset_post_sim_init()
+
+        for i, observer in enumerate(self.scenario.observers):
+            observer.data_store.set_storage_recorder(
+                observer.dynamics.storageUnit.storageUnitDataOutMsg.recorder()
+            )
+            logger.debug(
+                f"Logging {len(self.scenario.rso.dynamics.rso_points)} access points"
+            )
+            for rso_point_model in self.scenario.rso.dynamics.rso_points:
+                observer.data_store.add_point_access_recorder(
+                    rso_point_model.accessOutMsgs[i].recorder()
+                )
+
+    def initial_data(self, satellite: Satellite) -> Data:
+        if not issubclass(satellite.dyn_type, RSOImagingDynModel):
+            return RSOInspectionData()
+
+        return RSOInspectionData({point: False for point in self.scenario.rso_points})
+
+    def calculate_reward(self, new_data_dict: dict[str, Data]) -> dict[str, float]:
+        total_points = len(self.scenario.rso_points)
+        reward = {}
+        total_new_points = 0
+        for satellite_id, data in new_data_dict.items():
+            if len(data.point_inspect_status) == 0:
+                continue
+
+            new_points = 0
+            for point, access in data.point_inspect_status.items():
+                if access and not self.data.point_inspect_status.get(point, False):
+                    new_points += 1
+
+            if new_points > 0:
+                logger.info(f"{satellite_id} inspected {new_points} new points.")
+
+            reward[satellite_id] = (
+                new_points / total_points * self.inspection_reward_scale
+            )
+            total_new_points += new_points
+        if (
+            sum(self.data.point_inspect_status.values()) + total_new_points
+            == len(self.scenario.rso_points)
+            and not self.bonus_reward_yielded
+        ):
+            logger.info("All points inspected! Awarding completion bonus.")
+            for satellite_id in self.cum_reward:
+                reward[satellite_id] = (
+                    reward.get(satellite_id, 0.0) + self.completion_bonus
+                )
+            self.bonus_reward_yielded = True
+
+        return reward
+
+
+__doc_title__ = "RSO Inspection"
+__all__ = ["RSOInspectionReward", "RSOInspectionDataStore", "RSOInspectionData"]
diff --git a/src/bsk_rl/data/unique_image_data.py b/src/bsk_rl/data/unique_image_data.py
index ead45eb7..0697520f 100644
--- a/src/bsk_rl/data/unique_image_data.py
+++ b/src/bsk_rl/data/unique_image_data.py
@@ -6,6 +6,7 @@
 import numpy as np
 
 from bsk_rl.data.base import Data, DataStore, GlobalReward
+from bsk_rl.utils import vizard
 
 if TYPE_CHECKING:
     from bsk_rl.sats import Satellite
@@ -106,8 +107,16 @@ def compare_log_states(
             imaged.append(
                 [target for target in self.data.known if target.id == target_id][0]
             )
+        self.update_target_colors(imaged)
         return UniqueImageData(imaged=imaged)
 
+    @vizard.visualize
+    def update_target_colors(self, targets, vizInstance=None, vizSupport=None):
+        """Update target colors in Vizard."""
+        for location in vizInstance.locations:
+            if location.stationName in [target.name for target in targets]:
+                location.color = vizSupport.toRGBA255(self.satellite.vizard_color)
+
 
 class UniqueImageReward(GlobalReward):
     """GlobalReward for rewarding unique images."""
diff --git a/src/bsk_rl/gym.py b/src/bsk_rl/gym.py
index a2e88814..a71d5356 100644
--- a/src/bsk_rl/gym.py
+++ b/src/bsk_rl/gym.py
@@ -13,11 +13,12 @@
 
 from bsk_rl.comm import CommunicationMethod, NoCommunication
 from bsk_rl.data import GlobalReward, NoReward
+from bsk_rl.data.composition import ComposedReward
 from bsk_rl.sats import Satellite
 from bsk_rl.scene import Scenario
 from bsk_rl.sim import Simulator
 from bsk_rl.sim.world import WorldModel
-from bsk_rl.utils import logging_config
+from bsk_rl.utils import logging_config, vizard
 
 logger = logging.getLogger(__name__)
 
@@ -36,7 +37,7 @@ def __init__(
         self,
         satellites: Union[Satellite, list[Satellite]],
         scenario: Optional[Scenario] = None,
-        rewarder: Optional[GlobalReward] = None,
+        rewarder: Optional[Union[GlobalReward, list[GlobalReward]]] = None,
         world_type: Optional[type[WorldModel]] = None,
         world_args: Optional[dict[str, Any]] = None,
         communicator: Optional[CommunicationMethod] = None,
@@ -49,6 +50,8 @@ def __init__(
         generate_obs_retasking_only: bool = False,
         log_level: Union[int, str] = logging.WARNING,
         log_dir: Optional[str] = None,
+        vizard_dir: Optional[str] = None,
+        vizard_settings: Optional[dict[str, Any]] = None,
         render_mode=None,
     ) -> None:
         """A `Gymnasium <https://gymnasium.farama.org>`_ environment adaptable to a wide range satellite tasking problems.
@@ -68,7 +71,8 @@ def __init__(
             scenario: Environment the satellite is acting in; contains information
                 about targets, etc. See :ref:`bsk_rl.scene`.
             rewarder: Handles recording and rewarding for data collection towards
-                objectives. See :ref:`bsk_rl.data`.
+                objectives. Can be a single rewarder or a tuple of multiple rewarders.
+                See :ref:`bsk_rl.data`.
             communicator: Manages communication between satellites. See :ref:`bsk_rl.comm`.
             sat_arg_randomizer: For correlated randomization of satellites arguments. Should
                 be a function that takes a list of satellites and returns a dictionary that
@@ -91,10 +95,22 @@ def __init__(
                 zeros.
             log_level: Logging level for the environment. Default is ``WARNING``.
             log_dir: Directory to write logs to in addition to the console.
+            vizard_dir: Path to save Vizard visualization files. If None, no Vizard-related
+                modules will be imported.
+            vizard_settings: Settings for Vizard visualization. Set in ``vizIstance.settings``.
+                Additionally, the key ``vizard_rate`` can be set to the rate at which Vizard updates.
+                Valid setting can be found `here <https://hanspeterschaub.info/basilisk/Vizard/vizardAdvanced/vizardSettings.html#id1>`_.
             render_mode: Unused.
         """
         self.seed = None
         self._configure_logging(log_level, log_dir)
+        if vizard_dir is not None:
+            vizard.VIZARD_PATH = vizard_dir
+            if vizard_settings is not None:
+                logger.warning(
+                    "Vizard settings provided but Vizard is not enabled. Ignoring settings."
+                )
+        self.vizard_settings = vizard_settings if vizard_settings is not None else {}
 
         if isinstance(satellites, Satellite):
             satellites = [satellites]
@@ -125,8 +141,6 @@ def __init__(
 
         if scenario is None:
             scenario = Scenario()
-        if rewarder is None:
-            rewarder = NoReward()
 
         if world_type is None:
             world_type = self._minimum_world_model()
@@ -137,7 +151,16 @@ def __init__(
 
         self.scenario = deepcopy(scenario)
         self.scenario.link_satellites(self.satellites)
-        self.rewarder = deepcopy(rewarder)
+
+        rewarder = deepcopy(rewarder)
+        if rewarder is None:
+            rewarder = NoReward()
+        if (
+            isinstance(rewarder, Iterable)
+            and not type(rewarder).__name__ == "MagicMock"
+        ):
+            rewarder = ComposedReward(*rewarder)
+        self.rewarder = rewarder
         self.rewarder.link_scenario(self.scenario)
 
         if communicator is None:
@@ -250,8 +273,9 @@ def reset(
         self.scenario.reset_overwrite_previous()
         self.rewarder.reset_overwrite_previous()
         self.communicator.reset_overwrite_previous()
-        for satellite in self.satellites:
+        for i, satellite in enumerate(self.satellites):
             satellite.reset_overwrite_previous()
+            satellite.create_vizard_data(color=vizard.get_color(i))
         self.latest_step_duration = 0.0
 
         self._generate_world_args()
@@ -280,6 +304,13 @@ def reset(
             max_step_duration=self.max_step_duration,
             time_limit=self.time_limit,
         )
+        self.simulator.setup_vizard(**self.vizard_settings)
+
+        self.scenario.reset_during_sim_init()
+        self.rewarder.reset_during_sim_init()
+        self.communicator.reset_during_sim_init()
+
+        self.simulator.finish_init()
 
         self.scenario.reset_post_sim_init()
         self.rewarder.reset_post_sim_init()
@@ -389,7 +420,10 @@ def _step(self, actions: MultiSatAct) -> None:
             raise ValueError("There must be the same number of actions and satellites")
         for satellite, action in zip(self.satellites, actions):
             satellite.info = []  # reset satellite info log
-            if action is not None and action != NO_ACTION:
+            if action is not None and (
+                not isinstance(action, int)
+                or action != NO_ACTION  # TODO improve for non-discrete actions
+            ):
                 satellite.requires_retasking = False
                 satellite.set_action(action)
             if not satellite.is_alive():
diff --git a/src/bsk_rl/obs/__init__.py b/src/bsk_rl/obs/__init__.py
index cf2dc75d..98bb5594 100644
--- a/src/bsk_rl/obs/__init__.py
+++ b/src/bsk_rl/obs/__init__.py
@@ -40,6 +40,14 @@ class MyObservationSatellite(Satellite):
     SatProperties,
     Time,
 )
+from bsk_rl.obs.relative_observations import RelativeProperties
 
 __doc_title__ = "Observations"
-__all__ = ["Observation", "SatProperties", "Time", "OpportunityProperties", "Eclipse"]
+__all__ = [
+    "Observation",
+    "SatProperties",
+    "Time",
+    "OpportunityProperties",
+    "Eclipse",
+    "RelativeProperties",
+]
diff --git a/src/bsk_rl/obs/observations.py b/src/bsk_rl/obs/observations.py
index 43a48256..1417dfb0 100644
--- a/src/bsk_rl/obs/observations.py
+++ b/src/bsk_rl/obs/observations.py
@@ -48,7 +48,6 @@ def nested_obs_to_space(obs_dict):
 
 
 class ObservationBuilder:
-
     def __init__(self, satellite: "Satellite", obs_type: type = np.ndarray) -> None:
         """Satellite subclass for composing observations.
 
@@ -312,7 +311,6 @@ def _r_LB_H(sat, opp):
 
 
 class OpportunityProperties(Observation):
-
     _fn_map = {
         "priority": lambda sat, opp: opp["object"].priority,
         "r_LP_P": lambda sat, opp: opp["r_LP_P"],
diff --git a/src/bsk_rl/obs/relative_observations.py b/src/bsk_rl/obs/relative_observations.py
new file mode 100644
index 00000000..2e4cc3d4
--- /dev/null
+++ b/src/bsk_rl/obs/relative_observations.py
@@ -0,0 +1,167 @@
+"""Relative properties between two satellites."""
+
+from typing import Any
+
+import numpy as np
+
+from bsk_rl.obs import Observation
+from bsk_rl.utils.orbital import rv2omega
+
+
+def r_DC_N(deputy, chief):
+    """Relative position of the deputy satellite to the chief satellite in inertial frame."""
+    return np.array(deputy.dynamics.r_BN_N) - np.array(chief.dynamics.r_BN_N)
+
+
+def r_DC_C(deputy, chief):
+    """Relative position of the deputy satellite to the chief satellite in chief body frame."""
+    pass
+
+
+def r_DC_D(deputy, chief):
+    """Relative position of the deputy satellite to the chief satellite in deputy body frame."""
+    pass
+
+
+def r_DC_Hc(deputy, chief):
+    """Relative position of the deputy satellite to the chief satellite in chief Hill frame."""
+    HcN = chief.dynamics.HN
+    return HcN @ r_DC_N(deputy, chief)
+
+
+def r_DC_Hd(deputy, chief):
+    """Relative position of the deputy satellite to the chief satellite in deputy Hill frame."""
+    pass
+
+
+def v_DC_N(deputy, chief):
+    """Relative velocity of the deputy satellite to the chief satellite in inertial frame."""
+    return np.array(deputy.dynamics.v_BN_N) - np.array(chief.dynamics.v_BN_N)
+
+
+def v_DC_C(deputy, chief):
+    """Relative velocity of the deputy satellite to the chief satellite in chief body frame."""
+    pass
+
+
+def v_DC_D(deputy, chief):
+    """Relative velocity of the deputy satellite to the chief satellite in deputy body frame."""
+    pass
+
+
+def v_DC_Hc(deputy, chief):
+    """Relative velocity of the deputy satellite to the chief satellite in chief Hill frame."""
+    HcN = chief.dynamics.HN
+    omega_HcN_N = rv2omega(chief.dynamics.r_BN_N, chief.dynamics.v_BN_N)
+    return HcN @ (v_DC_N(deputy, chief) - np.cross(omega_HcN_N, r_DC_N(deputy, chief)))
+
+
+def v_DC_Hd(deputy, chief):
+    """Relative velocity of the deputy satellite to the chief satellite in deputy Hill frame."""
+    pass
+
+
+def sigma_DC(deputy, chief):
+    """Relative attitude of the deputy satellite to the chief satellite."""
+    pass
+
+
+def sigma_DHc(deputy, chief):
+    """Relative attitude of the deputy satellite to the chief satellite in chief Hill frame."""
+    pass
+
+
+def sigma_HdC(deputy, chief):
+    """Relative attitude of the deputy satellite Hill frame to the chief satellite."""
+    pass
+
+
+def sigma_HdHc(deputy, chief):
+    """Relative attitude of the deputy satellite Hill frame to the chief satellite Hill frame."""
+    pass
+
+
+# TODO what omegas do we need? Could probably make some thing that generates these and
+#  the other relative properties (i.e. whether to use body or hill frame for each sat, what
+#  frame to express in)
+
+
+class RelativeProperties(Observation):
+    """Add arbitrary properties relative to some other satellite."""
+
+    def __init__(
+        self, *rel_properties: dict[str, Any], chief_name: str, name="rel_props"
+    ) -> None:
+        """Include properties relative to another satellite.
+
+        .. code-block:: python
+
+            obs.RelativeProperties(
+                dict(prop="r_DC_N", norm=1e3),
+                dict(prop="v_DC_N", norm=1e3),
+                chief_name="ChiefSat",
+            ),
+
+        Args:
+            rel_properties: Property specifications. Properties are optionally
+                normalized by some factor. Each observation is a dictionary with the keys:
+
+                * ``prop``: Name of function in :class:`~bsk_rl.obs.relative_observations`.
+                * ``norm`` `optional`: Value to normalize property by. Defaults to 1.0.
+                * ``name`` `optional`: Name of the observation element. Defaults to the value of ``prop``.
+                * ``fn`` `optional`: Alternatively, call a function that takes the deputy (self) and chief (other)
+                  as arguments.
+            chief_name: Name of the satellite to compare against.
+            name: Name of the observation.
+
+        """
+        super().__init__(name=name)
+
+        for rel_property in rel_properties:
+            for key in rel_property:
+                if key not in ["prop", "norm", "name", "fn"]:
+                    raise ValueError(f"Invalid property key: {key}")
+            if "norm" not in rel_property:
+                rel_property["norm"] = 1.0
+            if "fn" not in rel_property:
+                try:
+                    rel_property["fn"] = globals()[rel_property["prop"]]
+                except KeyError:
+                    raise ValueError(
+                        f"Property prop={rel_property['prop']} is not predefined and no `fn` was provided."
+                    )
+            if "name" not in rel_property:
+                rel_property["name"] = rel_property["prop"]
+                if rel_property["norm"] != 1.0:
+                    rel_property["name"] += "_normd"
+
+        self.rel_properties = rel_properties
+        self.chief_name = chief_name
+
+    def reset_post_sim_init(self) -> None:
+        """Connect to the chief satellite.
+
+        :meta private:
+        """
+        try:
+            self.chief = [
+                sat
+                for sat in self.satellite.simulator.satellites
+                if sat.name == self.chief_name
+            ][0]
+        except IndexError:
+            raise ValueError(f"Chief satellite {self.chief_name} not found")
+
+    def get_obs(self) -> dict[str, Any]:
+        """Return the observation.
+
+        :meta private:
+        """
+        obs = {}
+        for rel_property in self.rel_properties:
+            value = rel_property["fn"](self.satellite, self.chief)
+            if isinstance(value, list):
+                value = np.array(value)
+            norm = rel_property["norm"]
+            obs[rel_property["name"]] = value / norm
+        return obs
diff --git a/src/bsk_rl/sats/access_satellite.py b/src/bsk_rl/sats/access_satellite.py
index ef19b0bf..3ecd3c03 100644
--- a/src/bsk_rl/sats/access_satellite.py
+++ b/src/bsk_rl/sats/access_satellite.py
@@ -11,6 +11,7 @@
 from bsk_rl.sats.satellite import Satellite
 from bsk_rl.scene.targets import Target
 from bsk_rl.sim import dyn, fsw
+from bsk_rl.utils import vizard
 from bsk_rl.utils.functional import valid_func_name
 from bsk_rl.utils.orbital import elevation
 
@@ -583,6 +584,7 @@ def _update_image_event(self, target: "Target") -> None:
                     self._info_command(f"imaged {target}"),
                     self._satellite_command + ".imaged += 1",
                     self._satellite_command + ".requires_retasking = True",
+                    self._satellite_command + ".remove_imaging_line()",
                 ],
                 terminal=self.variable_interval,
             )
@@ -640,7 +642,10 @@ def enable_target_window(self, target: "Target"):
         self.update_timed_terminal_event(
             next_window[1],
             info=f"for {target} window",
-            extra_actions=[self._satellite_command + ".missed += 1"],
+            extra_actions=[
+                self._satellite_command + ".missed += 1",
+                self._satellite_command + ".remove_imaging_line()",
+            ],
         )
 
     def task_target_for_imaging(self, target: "Target"):
@@ -653,3 +658,27 @@ def task_target_for_imaging(self, target: "Target"):
         self.logger.info(msg)
         self.fsw.action_image(target.r_LP_P, target.id)
         self.enable_target_window(target)
+        self.draw_imaging_line(target)
+
+    @vizard.visualize
+    def draw_imaging_line(
+        self, target: "Target", vizSupport=None, vizInstance=None
+    ) -> None:
+        """Draw a line from the satellite to the target in vizard."""
+        if not hasattr(self, "target_line"):
+            vizSupport.createTargetLine(
+                vizInstance,
+                fromBodyName=self.name,
+                toBodyName=target.name,
+                lineColor=self.vizard_color,
+            )
+            self.target_line = vizSupport.targetLineList[-1]
+        self.target_line.toBodyName = target.name
+        vizSupport.updateTargetLineList(vizInstance)
+
+    @vizard.visualize
+    def remove_imaging_line(self, vizSupport=None, vizInstance=None):
+        """Remove the imaging line from Vizard."""
+        if hasattr(self, "target_line"):
+            self.target_line.toBodyName = self.name
+            vizSupport.updateTargetLineList(vizInstance)
diff --git a/src/bsk_rl/sats/satellite.py b/src/bsk_rl/sats/satellite.py
index ea482d11..cc31d577 100644
--- a/src/bsk_rl/sats/satellite.py
+++ b/src/bsk_rl/sats/satellite.py
@@ -14,6 +14,7 @@
 from bsk_rl.act.actions import select_action_builder
 from bsk_rl.obs.observations import ObservationBuilder
 from bsk_rl.sim import dyn, fsw
+from bsk_rl.utils import vizard
 from bsk_rl.utils.functional import (
     AbstractClassProperty,
     Resetable,
@@ -123,7 +124,7 @@ def generate_sat_args(self, **kwargs) -> None:
         for k, v in kwargs.items():
             if k not in self.sat_args:
                 raise KeyError(f"{k} not a valid key for sat_args")
-            if self.sat_args[k] != v:
+            if np.any(self.sat_args[k] != v):
                 self.logger.debug(
                     f"Overwriting {k}={self.sat_args[k]} in sat_args with {v}"
                 )
@@ -138,6 +139,14 @@ def reset_overwrite_previous(self) -> None:
         self._is_alive = True
         self.time_of_death = None
 
+    @vizard.visualize
+    def create_vizard_data(self, color, vizSupport=None) -> None:
+        """Create a location to store data to be passed to enableUnityVisualization."""
+        self.vizard_color = color
+        self.vizard_data = dict(
+            spriteList=vizSupport.setSprite("SQUARE", color=color),
+        )
+
     def reset_pre_sim_init(self) -> None:
         """Called during environment reset, before Basilisk simulation initialization."""
         self.trajectory = TrajectorySimulator(
diff --git a/src/bsk_rl/scene/__init__.py b/src/bsk_rl/scene/__init__.py
index 47bb17d2..e0d8e5ad 100644
--- a/src/bsk_rl/scene/__init__.py
+++ b/src/bsk_rl/scene/__init__.py
@@ -9,6 +9,9 @@
 """
 
 from bsk_rl.scene.scenario import Scenario, UniformNadirScanning
+
+pass  # Other imports must come after Scenario
+from bsk_rl.scene.rso_points import FibonacciSphereRSOPoints, RSOPoints
 from bsk_rl.scene.targets import CityTargets, UniformTargets
 
 __doc_title__ = "Scenario"
@@ -17,4 +20,6 @@
     "UniformTargets",
     "CityTargets",
     "UniformNadirScanning",
+    "RSOPoints",
+    "FibonacciSphereRSOPoints",
 ]
diff --git a/src/bsk_rl/scene/rso_points.py b/src/bsk_rl/scene/rso_points.py
new file mode 100644
index 00000000..ac776e03
--- /dev/null
+++ b/src/bsk_rl/scene/rso_points.py
@@ -0,0 +1,149 @@
+"""TODO: Add docstring."""
+
+import logging
+from abc import abstractmethod
+from dataclasses import dataclass
+from typing import TYPE_CHECKING
+
+import numpy as np
+import pandas as pd
+
+from bsk_rl.scene import Scenario
+from bsk_rl.sim.dyn import RSODynModel, RSOImagingDynModel
+from bsk_rl.sim.fsw import RSOImagingFSWModel
+from bsk_rl.utils import vizard
+
+if TYPE_CHECKING:  # pragma: no cover
+    from bsk_rl.data.base import Data
+    from bsk_rl.sats import Satellite
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class RSOPoint:
+    r_PB_B: np.ndarray
+    n_B: np.ndarray
+    theta_min: float
+    range: float
+
+    def __hash__(self) -> int:
+        """Hash target by unique id."""
+        return hash(id(self))  # THIS IS ALMOST CERTAINLY A BAD IDEA
+
+    def __str__(self) -> str:
+        return f"RSOPoint_{self.r_PB_B}"
+
+
+class RSOPoints(Scenario):
+    def reset_overwrite_previous(self) -> None:
+        """Overwrite target list from previous episode."""
+        self.rso_points = []
+
+    def reset_pre_sim_init(self) -> None:
+        self.rso_points = self.generate_points()
+
+        # Check for RSOs and observers
+        rsos = [sat for sat in self.satellites if issubclass(sat.dyn_type, RSODynModel)]
+        if len(rsos) == 0:
+            logger.warning("No RSODynModel satellites found in scenario.")
+            return
+        assert len(rsos) == 1, "Only one RSODynModel satellite is supported."
+        self.rso = rsos[0]
+
+        self.observers = [
+            sat
+            for sat in self.satellites
+            if issubclass(sat.dyn_type, RSOImagingDynModel)
+        ]
+        if len(self.observers) == 0:
+            logger.warning("No RSOImagingDynModel satellites found in scenario.")
+            return
+
+        return super().reset_pre_sim_init()
+
+    def reset_during_sim_init(self) -> None:
+        # Add points to dynamics and fsw of RSO
+        assert isinstance(self.rso.dynamics, RSODynModel)
+        logger.debug("Adding inspection points to RSO and observers")
+        for point in self.rso_points:
+            rso_point_model = self.rso.dynamics.add_rso_point(
+                point.r_PB_B, point.n_B, point.theta_min, point.range
+            )
+            # Add point to each observer
+            for observer in self.observers:
+                assert isinstance(observer.dynamics, RSOImagingDynModel)
+                assert isinstance(observer.fsw, RSOImagingFSWModel)
+                observer.dynamics.add_rso_point(rso_point_model)
+
+            self.visualize_rso_point(point)
+
+        logger.debug("Targeting RSO with observers")
+        for observer in self.observers:
+            observer.fsw.set_target_rso(self.rso)
+
+    @vizard.visualize
+    def visualize_rso_point(self, rso_point, vizSupport=None, vizInstance=None):
+        """Visualize target in Vizard."""
+        vizSupport.addLocation(
+            vizInstance,
+            stationName=str(rso_point),
+            parentBodyName=self.rso.name,
+            r_GP_P=list(rso_point.r_PB_B),
+            gHat_P=list(rso_point.n_B),
+            fieldOfView=rso_point.theta_min,
+            color=vizSupport.toRGBA255("tab:red", alpha=0.5),
+            range=float(rso_point.range),
+        )
+        vizInstance.settings.showLocationCones = -1
+        vizInstance.settings.showLocationCommLines = -1
+        vizInstance.settings.showLocationLabels = -1
+
+    @abstractmethod
+    def generate_points(self) -> list[RSOPoint]:
+        pass
+
+
+class FibonacciSphereRSOPoints(RSOPoints):
+    def __init__(
+        self,
+        n_points: int = 100,
+        radius: float = 1.0,
+        theta_min: float = np.radians(45),
+        range: float = -1,
+        # incidence_min: float = np.radians(60),  # TODO handle
+    ):
+        self.n_points = n_points
+        self.radius = radius
+        self.theta_min = theta_min
+        self.range = range
+        # self.incidence_min = incidence_min
+
+    def generate_points(self) -> list[RSOPoint]:
+        points = []
+
+        # https://gist.github.com/Seanmatthews/a51ac697db1a4f58a6bca7996d75f68c
+        ga = (3 - np.sqrt(5)) * np.pi  # golden angle
+        theta = ga * np.arange(self.n_points)
+        z = np.linspace(1 / self.n_points - 1, 1 - 1 / self.n_points, self.n_points)
+        radius = np.sqrt(1 - z * z)
+        y = radius * np.sin(theta)
+        x = radius * np.cos(theta)
+
+        for i in range(self.n_points):
+            r_PB_B = np.array([x[i], y[i], z[i]]) * self.radius
+            n_B = np.array([x[i], y[i], z[i]])
+            points.append(
+                RSOPoint(
+                    r_PB_B,
+                    n_B,
+                    self.theta_min,
+                    self.range,
+                )
+            )
+
+        return points
+
+
+__doc_title__ = "RSO Scenarios"
+__all__ = ["RSOPoints"]
diff --git a/src/bsk_rl/scene/targets.py b/src/bsk_rl/scene/targets.py
index 77a62ccd..ccf4e0bd 100644
--- a/src/bsk_rl/scene/targets.py
+++ b/src/bsk_rl/scene/targets.py
@@ -15,6 +15,7 @@
 from Basilisk.utilities import orbitalMotion
 
 from bsk_rl.scene import Scenario
+from bsk_rl.utils import vizard
 from bsk_rl.utils.orbital import lla2ecef
 
 if TYPE_CHECKING:  # pragma: no cover
@@ -115,6 +116,27 @@ def reset_pre_sim_init(self) -> None:
                         type="target",
                     )
 
+    def reset_during_sim_init(self) -> None:
+        """Visualize targets in Vizard on reset."""
+        for target in self.targets:
+            self.visualize_target(target)
+
+    @vizard.visualize
+    def visualize_target(self, target, vizSupport=None, vizInstance=None):
+        """Visualize target in Vizard."""
+        vizSupport.addLocation(
+            vizInstance,
+            stationName=target.name,
+            parentBodyName="earth",
+            r_GP_P=list(target.r_LP_P),
+            fieldOfView=np.arctan(500 / 800),
+            color=vizSupport.toRGBA255("white"),
+            range=1000.0 * 1000,  # meters
+        )
+        vizInstance.settings.showLocationCones = -1
+        vizInstance.settings.showLocationCommLines = -1
+        vizInstance.settings.showLocationLabels = -1
+
     def regenerate_targets(self) -> None:
         """Regenerate targets uniformly.
 
@@ -188,7 +210,7 @@ def regenerate_targets(self) -> None:
             location *= self.radius
             self.targets.append(
                 Target(
-                    name=city["city"].replace("'", ""),
+                    name=f"{city['city']}, {city['iso2']}".replace("'", ""),
                     r_LP_P=location,
                     priority=self.priority_distribution(),
                 )
diff --git a/src/bsk_rl/sim/dyn.py b/src/bsk_rl/sim/dyn.py
index 479027ee..28789db4 100644
--- a/src/bsk_rl/sim/dyn.py
+++ b/src/bsk_rl/sim/dyn.py
@@ -70,6 +70,7 @@
     aliveness_checker,
     check_aliveness_checkers,
     default_args,
+    valid_func_name,
 )
 from bsk_rl.utils.orbital import random_orbit, rv2HN, rv2omega
 
@@ -211,6 +212,11 @@ def BP(self):
         """Body relative to planet freame rotation matrix."""
         return np.matmul(self.BN, self.world.PN.T)
 
+    @property
+    def HN(self):
+        """Hill frame relative to inertial frame rotation matrix."""
+        return rv2HN(self.r_BN_N, self.v_BN_N)
+
     @property
     def r_BN_N(self):
         """Body position relative to inertial origin in inertial frame [m]."""
@@ -338,7 +344,7 @@ def setup_spacecraft_hub(
             raise (KeyError("Orbit is overspecified. Provide either (rN, vN) or oe"))
 
         self.scObject = spacecraft.Spacecraft()
-        self.scObject.ModelTag = "sat-" + self.satellite.name
+        self.scObject.ModelTag = self.satellite.name
 
         Ixx = 1.0 / 12.0 * mass * (width**2.0 + depth**2.0)
         Iyy = 1.0 / 12.0 * mass * (depth**2.0 + height**2.0)
@@ -1185,6 +1191,129 @@ def __init__(self, *args, **kwargs) -> None:
         super().__init__(*args, **kwargs)
 
 
+class ConjunctionDynModel(BasicDynamicsModel):
+    """For evaluating conjunctions between satellites."""
+
+    def __init__(self, *args, **kwargs) -> None:
+        """For evaluating conjunctions between satellites."""
+        super().__init__(*args, **kwargs)
+        self.conjunctions = []
+
+    def _setup_dynamics_objects(self, **kwargs) -> None:
+        super()._setup_dynamics_objects(**kwargs)
+        self.setup_conjunctions(**kwargs)
+
+    @aliveness_checker
+    def conjunction_valid(self) -> bool:
+        """Check if conjunction has not occured."""
+        return len(self.conjunctions) == 0
+
+    @default_args(conjunction_radius=10)
+    def setup_conjunctions(self, conjunction_radius: float, **kwargs) -> None:
+        """Set up conjunction checking between satellites.
+
+        Args:
+            conjunction_radius: [m] Minimum distance for a conjunction.
+            kwargs: Passed to other setup functions.
+        """
+        self.conjunction_radius = conjunction_radius
+
+        for sat_dyn in self.simulator.dynamics_list.values():
+            if sat_dyn != self and isinstance(sat_dyn, ConjunctionDynModel):
+                self.simulator.createNewEvent(
+                    valid_func_name(
+                        f"conjunction_{self.satellite.name}_{sat_dyn.satellite.name}"
+                    ),
+                    macros.sec2nano(self.simulator.sim_rate),
+                    True,
+                    [
+                        f"np.linalg.norm(np.array({self.satellite._satellite_command}.dynamics.r_BN_N) - np.array({sat_dyn.satellite._satellite_command}.dynamics.r_BN_N))"
+                        + " <= "
+                        + f"{self.satellite._satellite_command}.dynamics.conjunction_radius + {sat_dyn.satellite._satellite_command}.dynamics.conjunction_radius"
+                    ],
+                    [
+                        self.satellite._info_command(
+                            f"collided with {sat_dyn.satellite.name}"
+                        ),
+                        sat_dyn.satellite._info_command(
+                            f"collided with {self.satellite.name}"
+                        ),
+                        f"{self.satellite._satellite_command}.dynamics.conjunctions.append({sat_dyn.satellite._satellite_command})",
+                        f"{sat_dyn.satellite._satellite_command}.dynamics.conjunctions.append({self.satellite._satellite_command})",
+                    ],
+                    terminal=True,
+                )
+
+
+class RSODynModel(BasicDynamicsModel):
+    """For an RSO with points targets for observation."""
+
+    def __init__(self, *args, **kwargs) -> None:
+        """Allow for body fixed inspection points to be added to a spacecraft.
+
+        Works with :class:`~bsk_rl.sats.RSOImagingSatellite`.
+        """
+        super().__init__(*args, **kwargs)
+
+    def _setup_dynamics_objects(self, **kwargs) -> None:
+        super()._setup_dynamics_objects(**kwargs)
+
+        rso_dyn_proc_name = "RSODynProcess"
+        self.rso_dyn_proc = self.simulator.CreateNewProcess(rso_dyn_proc_name, 1)
+        self.rso_task_name = "RSODynTask"
+        self.rso_dyn_proc.addTask(
+            self.simulator.CreateNewTask(
+                self.rso_task_name, macros.sec2nano(self.dyn_rate)
+            )
+        )
+
+        self.rso_points = []
+
+    def add_rso_point(self, r_LB_B, aHat_B, theta, range):
+        rso_point_model = spacecraftLocation.SpacecraftLocation()
+        rso_point_model.primaryScStateInMsg.subscribeTo(self.scObject.scStateOutMsg)
+
+        rso_point_model.planetInMsg.subscribeTo(
+            self.world.gravFactory.spiceObject.planetStateOutMsgs[self.world.body_index]
+        )
+        rso_point_model.rEquator = self.simulator.world.planet.radEquator
+        rso_point_model.rPolar = self.simulator.world.planet.radEquator * 0.98
+
+        rso_point_model.sunInMsg.subscribeTo(
+            self.world.gravFactory.spiceObject.planetStateOutMsgs[self.world.sun_index]
+        )
+        rso_point_model.eclipseInMsg.subscribeTo(
+            self.world.eclipseObject.eclipseOutMsgs[self.eclipse_index]
+        )
+
+        rso_point_model.r_LB_B = r_LB_B
+        rso_point_model.aHat_B = aHat_B
+        rso_point_model.theta = theta
+        rso_point_model.theta_solar = 0.9 * np.pi / 2
+        rso_point_model.shadow_factor_limit = 0.1
+        rso_point_model.maximumRange = range
+        self.simulator.AddModelToTask(
+            self.rso_task_name, rso_point_model, ModelPriority=1
+        )
+
+        self.rso_points.append(rso_point_model)
+        return rso_point_model
+
+
+class RSOImagingDynModel(ContinuousImagingDynModel):
+    """For a satellite observing points on an RSO."""
+
+    def __init__(self, *args, **kwargs) -> None:
+        """Allow a satellite to observe points in a RSO.
+
+        Works with :class:`~bsk_rl.sats.RSOImagingSatellite`.
+        """
+        super().__init__(*args, **kwargs)
+
+    def add_rso_point(self, rso_point_model):
+        rso_point_model.addSpacecraftToModel(self.scObject.scStateOutMsg)
+
+
 __doc_title__ = "Dynamics Sims"
 __all__ = [
     "DynamicsModel",
@@ -1193,5 +1322,8 @@ def __init__(self, *args, **kwargs) -> None:
     "ImagingDynModel",
     "ContinuousImagingDynModel",
     "GroundStationDynModel",
+    "ConjunctionDynModel",
     "FullFeaturedDynModel",
+    "RSODynModel",
+    "RSOImagingDynModel",
 ]
diff --git a/src/bsk_rl/sim/fsw.py b/src/bsk_rl/sim/fsw.py
index 58a36777..147e421f 100644
--- a/src/bsk_rl/sim/fsw.py
+++ b/src/bsk_rl/sim/fsw.py
@@ -55,8 +55,10 @@
 from Basilisk.utilities import macros as mc
 
 from bsk_rl.sim import dyn
+from bsk_rl.utils import vizard
 from bsk_rl.utils.functional import (
     AbstractClassProperty,
+    aliveness_checker,
     check_aliveness_checkers,
     default_args,
 )
@@ -70,7 +72,7 @@
 
 
 def action(
-    func: Callable[..., None]
+    func: Callable[..., None],
 ) -> Callable[Callable[..., None], Callable[..., None]]:
     """Decorator to reset the satellite software before executing an action.
 
@@ -635,6 +637,12 @@ def c_hat_P(self):
         c_hat_B = self.locPoint.pHat_B
         return np.matmul(self.dynamics.BP.T, c_hat_B)
 
+    @property
+    def c_hat_N(self):
+        """Instrument pointing direction in the inertial frame."""
+        c_hat_B = self.locPoint.pHat_B
+        return np.matmul(self.dynamics.BN.T, c_hat_B)
+
     @property
     def c_hat_H(self):
         """Instrument pointing direction in the hill frame."""
@@ -674,6 +682,7 @@ def _create_module_data(self) -> None:
         def _setup_fsw_objects(self, **kwargs) -> None:
             self.setup_location_pointing(**kwargs)
             self.setup_instrument_controller(**kwargs)
+            self.show_sensor()
 
         @default_args(inst_pHat_B=[0, 0, 1])
         def setup_location_pointing(
@@ -734,6 +743,21 @@ def setup_instrument_controller(
 
             self._add_model_to_task(self.insControl, priority=987)
 
+        @vizard.visualize
+        def show_sensor(self, vizInterface=None, vizSupport=None):
+            """Visualize the sensor in Vizard."""
+            genericSensor = vizInterface.GenericSensor()
+            genericSensor.normalVector = self.locPoint.pHat_B
+            genericSensor.r_SB_B = [0.0, 0.0, 0.0]
+            genericSensor.fieldOfView.push_back(4 * self.insControl.attErrTolerance)
+            genericSensor.color = vizInterface.IntVector(
+                vizSupport.toRGBA255(self.fsw.satellite.vizard_color, alpha=0.5)
+            )
+            cmdInMsg = messaging.DeviceCmdMsgReader()
+            cmdInMsg.subscribeTo(self.insControl.deviceCmdOutMsg)
+            genericSensor.genericSensorCmdInMsg = cmdInMsg
+            self.fsw.satellite.vizard_data["genericSensorList"] = [genericSensor]
+
         def reset_for_action(self) -> None:
             """Reset pointing controller."""
             self.fsw.dynamics.imagingTarget.Reset(self.fsw.simulator.sim_time_ns)
@@ -988,6 +1012,140 @@ def __init__(self, *args, **kwargs) -> None:
         super().__init__(*args, **kwargs)
 
 
+class MagicOrbitalManeuverFSWModel(BasicFSWModel):
+    """Model that allows for instantaneous Delta V maneuvers."""
+
+    def __init__(self, *args, **kwargs) -> None:
+        """Model that allows for instantaneous Delta V maneuvers."""
+        super().__init__(*args, **kwargs)
+        self.setup_fuel(**kwargs)
+        self.thrust_count = 0
+
+    @property
+    def dv_available(self):
+        """Delta-V available for the satellite."""
+        return self._dv_available
+
+    @aliveness_checker
+    def fuel_remaining(self) -> bool:
+        """Check if the satellite has fuel remaining."""
+        return self.dv_available > 0
+
+    @default_args(dv_available_init=100.0)
+    def setup_fuel(self, dv_available_init: float, **kwargs):
+        """Set up available fuel for the satellite.
+
+        # TODO: may adjust names for consistency with modelled fuel take in future.
+
+        Args:
+            dv_available_init: [m/s] Initial fuel level.
+            kwargs: Passed to other setup functions.
+        """
+        self._dv_available = dv_available_init
+
+    @action
+    def action_magic_thrust(self, dv_N: np.ndarray) -> None:
+        """Thrust relative to the inertial frame.
+
+        Args:
+            dv_N: [m/s] Inertial Delta V.
+        """
+        if np.linalg.norm(dv_N) > self.dv_available:
+            self.satellite.logger.warning(
+                f"Maneuver exceeds available Delta V ({np.linalg.norm(dv_N)}/{self.dv_available} m/s)."
+            )
+
+        self._dv_available -= np.linalg.norm(dv_N)
+
+        self.dynamics.scObject.dynManager.getStateObject(
+            self.dynamics.scObject.hub.nameOfHubVelocity
+        ).setState(list(np.array(self.dynamics.v_BN_N) + np.array(dv_N)))
+
+        self.thrust_count += 1
+
+
+class RSOImagingFSWModel(ContinuousImagingFSWModel):
+    def set_target_rso(self, rso: "Satellite") -> None:
+        self.locPoint.scTargetInMsg.subscribeTo(
+            rso.dynamics.simpleNavObject.transOutMsg
+        )
+
+    class LocPointTask(ContinuousImagingFSWModel.LocPointTask):
+        """Task to point at the RSO and trigger the instrument."""
+
+        def __init__(self, *args, **kwargs) -> None:
+            """Task to point at the RSO and trigger the instrument."""
+            super().__init__(*args, **kwargs)
+
+        @default_args(inst_pHat_B=[0, 0, 1])  # TODO
+        def setup_location_pointing(
+            self, inst_pHat_B: Iterable[float], **kwargs
+        ) -> None:
+            """Set the location pointing guidance module to point at the RSO.
+
+            ``set_target_rso`` must be called externally to connect the RSO to the pointing module.
+
+            Args:
+                inst_pHat_B: Instrument pointing direction.
+                kwargs: Passed to other setup functions.
+            """
+            self.locPoint.pHat_B = inst_pHat_B
+            self.locPoint.scAttInMsg.subscribeTo(
+                self.fsw.dynamics.simpleNavObject.attOutMsg
+            )
+            self.locPoint.scTransInMsg.subscribeTo(
+                self.fsw.dynamics.simpleNavObject.transOutMsg
+            )
+            self.locPoint.useBoresightRateDamping = 1
+            messaging.AttGuidMsg_C_addAuthor(
+                self.locPoint.attGuidOutMsg, self.fsw.attGuidMsg
+            )
+
+            self._add_model_to_task(self.locPoint, priority=1198)
+
+        @default_args(imageAttErrorRequirement=0.01, imageRateErrorRequirement=None)
+        def setup_instrument_controller(  # TODO
+            self,
+            imageAttErrorRequirement: float,
+            imageRateErrorRequirement: float,
+            **kwargs,
+        ) -> None:
+            """Set the instrument controller parameters for scanning.
+
+            As long as these two conditions are met, scanning will occur continuously.
+
+            Args:
+                imageAttErrorRequirement: [MRP norm] Pointing attitude error tolerance
+                    for imaging.
+                imageRateErrorRequirement: [rad/s] Rate tolerance for imaging. Disable
+                    with None.
+                kwargs: Passed to other setup functions.
+            """
+            self.insControl.attErrTolerance = imageAttErrorRequirement
+            if imageRateErrorRequirement is not None:
+                self.insControl.useRateTolerance = 1
+                self.insControl.rateErrTolerance = imageRateErrorRequirement
+            self.insControl.attGuidInMsg.subscribeTo(self.fsw.attGuidMsg)
+            # Only use this module to check for pointing requirements
+            self.access_msg = messaging.AccessMsg()
+            payload = messaging.AccessMsgPayload()
+            payload.hasAccess = 1
+            self.access_msg.write(payload)
+            self.insControl.accessInMsg.subscribeTo(self.access_msg)
+
+            self._add_model_to_task(self.insControl, priority=987)
+
+    @action
+    def action_inspect_rso(self) -> None:
+        self.dynamics.instrument.nodeStatusInMsg.subscribeTo(
+            self.insControl.deviceCmdOutMsg
+        )
+        self.insControl.controllerStatus = 1
+        self.dynamics.instrumentPowerSink.powerStatus = 1
+        self.dynamics.instrument.nodeDataName = "inspect_rso"
+        self.simulator.enableTask(self.LocPointTask.name + self.satellite.name)
+
+
 __doc_title__ = "FSW Sims"
 __all__ = [
     "action",
@@ -996,4 +1154,5 @@ def __init__(self, *args, **kwargs) -> None:
     "ContinuousImagingFSWModel",
     "SteeringFSWModel",
     "SteeringImagerFSWModel",
+    "MagicOrbitalManeuverFSWModel",
 ]
diff --git a/src/bsk_rl/sim/simulator.py b/src/bsk_rl/sim/simulator.py
index 09d5834c..02dce636 100644
--- a/src/bsk_rl/sim/simulator.py
+++ b/src/bsk_rl/sim/simulator.py
@@ -1,11 +1,16 @@
 """Extended Basilisk SimBaseClass for GeneralSatelliteTasking environments."""
 
 import logging
+import os
+from pathlib import Path
+from time import time
 from typing import TYPE_CHECKING, Any
 
 from Basilisk.utilities import SimulationBaseClass
 from Basilisk.utilities import macros as mc
 
+from bsk_rl.utils import vizard
+
 if TYPE_CHECKING:  # pragma: no cover
     from bsk_rl.sats import Satellite
     from bsk_rl.sim.world import WorldModel
@@ -57,6 +62,9 @@ def __init__(
             self.dynamics_list[satellite.name] = satellite.set_dynamics(self.sim_rate)
             self.fsw_list[satellite.name] = satellite.set_fsw(self.sim_rate)
 
+    def finish_init(self) -> None:
+        """Finish simulator initialization."""
+        self.set_vizard_epoch()
         self.InitializeSimulation()
         self.ConfigureStopTime(0)
         self.ExecuteSimulation()
@@ -71,6 +79,44 @@ def sim_time(self) -> float:
         """Simulation time in seconds, tied to SimBase integrator."""
         return self.sim_time_ns * mc.NANO2SEC
 
+    @vizard.visualize
+    def setup_vizard(self, vizard_rate=None, vizSupport=None, **vizard_settings):
+        """Setup Vizard for visualization."""
+        save_path = Path(vizard.VIZARD_PATH)
+        if not save_path.exists():
+            os.makedirs(save_path, exist_ok=True)
+
+        viz_proc_name = "VizProcess"
+        viz_proc = self.CreateNewProcess(viz_proc_name, priority=400)
+
+        # Define process name, task name and task time-step
+        viz_task_name = "viz_task_name"
+        if vizard_rate is None:
+            vizard_rate = self.sim_rate
+        viz_proc.addTask(self.CreateNewTask(viz_task_name, mc.sec2nano(vizard_rate)))
+
+        customizers = ["spriteList", "genericSensorList"]
+        list_data = {}
+        for customizer in customizers:
+            list_data[customizer] = [
+                sat.vizard_data.get(customizer, None) for sat in self.satellites
+            ]
+        self.vizInstance = vizSupport.enableUnityVisualization(
+            self,
+            viz_task_name,
+            scList=[sat.dynamics.scObject for sat in self.satellites],
+            **list_data,
+            saveFile=save_path / f"viz_{time()}",
+        )
+        for key, value in vizard_settings.items():
+            setattr(self.vizInstance.settings, key, value)
+        vizard.VIZINSTANCE = self.vizInstance
+
+    @vizard.visualize
+    def set_vizard_epoch(self, vizInstance=None):
+        """Set the Vizard epoch."""
+        vizInstance.epochInMsg.subscribeTo(self.world.gravFactory.epochMsg)
+
     def _set_world(
         self, world_type: type["WorldModel"], world_args: dict[str, Any]
     ) -> None:
diff --git a/src/bsk_rl/sim/world.py b/src/bsk_rl/sim/world.py
index e4f8ff98..957d50e4 100644
--- a/src/bsk_rl/sim/world.py
+++ b/src/bsk_rl/sim/world.py
@@ -178,7 +178,7 @@ def setup_gravity_bodies(
         # setup Spice interface for some solar system bodies
         timeInitString = utc_init
         self.gravFactory.createSpiceInterface(
-            bsk_path + "/supportData/EphemerisData/", timeInitString
+            bsk_path + "/supportData/EphemerisData/", timeInitString, epochInMsg=True
         )
         self.gravFactory.spiceObject.zeroBase = "earth"
 
diff --git a/src/bsk_rl/utils/functional.py b/src/bsk_rl/utils/functional.py
index 9b3dbd7e..3aceb955 100644
--- a/src/bsk_rl/utils/functional.py
+++ b/src/bsk_rl/utils/functional.py
@@ -200,6 +200,10 @@ def reset_pre_sim_init(self) -> None:
         """Reset before simulator initialization."""
         pass
 
+    def reset_during_sim_init(self) -> None:
+        """Reset after simulator models have been created but before the simulator is initialized."""
+        pass
+
     def reset_post_sim_init(self) -> None:
         """Reset after simulator initialization."""
         pass
diff --git a/src/bsk_rl/utils/orbital.py b/src/bsk_rl/utils/orbital.py
index 4b9ba526..94495b80 100644
--- a/src/bsk_rl/utils/orbital.py
+++ b/src/bsk_rl/utils/orbital.py
@@ -1,7 +1,7 @@
 """``bsk_rl.utils.orbital``:Utilities for computing orbital events."""
 
 import logging
-from typing import Iterable, Optional
+from typing import Callable, Iterable, Optional, Tuple, Union
 
 import numpy as np
 from Basilisk import __path__
@@ -12,7 +12,7 @@
     orbitalMotion,
     simIncludeGravBody,
 )
-from Basilisk.utilities.orbitalMotion import ClassicElements, elem2rv
+from Basilisk.utilities.orbitalMotion import ClassicElements, elem2rv, rv2elem
 from scipy.interpolate import interp1d
 
 bskPath = __path__[0]
@@ -20,6 +20,16 @@
 logger = logging.getLogger(__name__)
 
 
+def random_unit_vector() -> np.ndarray:
+    """Generate a random unit vector.
+
+    Returns:
+        Random unit vector
+    """
+    vec = np.random.randn(3)
+    return vec / np.linalg.norm(vec)
+
+
 def random_orbit(
     i: Optional[float] = 45.0,
     alt: float = 500,
@@ -236,6 +246,48 @@ def walker_delta_arg_setup(satellites):
     return walker_delta_arg_setup
 
 
+def relative_to_chief(
+    chief_name: str,
+    chief_orbit: Union[ClassicElements, Callable],
+    deputy_relative_state: dict[str, Union[np.ndarray, Callable]],
+):
+    def walker_delta_arg_setup(satellites):
+        args = {sat: {} for sat in satellites}
+
+        chief = [satellite for satellite in satellites if satellite.name == chief_name][
+            0
+        ]
+        mu = chief.sat_args_generator["mu"]
+
+        if isinstance(chief_orbit, ClassicElements):
+            args[chief]["oe"] = chief_orbit
+        else:
+            args[chief]["oe"] = chief_orbit()
+
+        rc_N, vc_N = elem2rv(mu, args[chief]["oe"])
+
+        for satellite_name, relative_state in deputy_relative_state.items():
+            deputy = [
+                satellite
+                for satellite in satellites
+                if satellite.name == satellite_name
+            ][0]
+
+            if not isinstance(relative_state, list) and not isinstance(
+                relative_state, np.ndarray
+            ):
+                relative_state = relative_state()
+
+            rho_H = relative_state[0:3]
+            rho_deriv_H = relative_state[3:6]
+            rd_N, vd_N = hill2cd(rc_N, vc_N, rho_H, rho_deriv_H)
+            args[deputy]["oe"] = rv2elem(mu, rd_N, vd_N)
+
+        return args
+
+    return walker_delta_arg_setup
+
+
 class TrajectorySimulator(SimulationBaseClass.SimBaseClass):
     """Class for propagating trajectory using a point mass simulation."""
 
@@ -502,8 +554,41 @@ def rv2omega(r_N: np.ndarray, v_N: np.ndarray):
     return omega_HN_N
 
 
+def cd2hill(
+    rc_N: np.ndarray, vc_N: np.ndarray, rd_N: np.ndarray, vd_N: np.ndarray
+) -> Tuple[np.ndarray, np.ndarray]:
+    h_N = np.cross(rc_N, vc_N)
+    o_h_N = h_N / np.linalg.norm(h_N)
+    ON = rv2HN(rc_N, vc_N)
+
+    f_dot = np.linalg.norm(h_N) / np.linalg.norm(rc_N) ** 2
+    omega_ON_N = f_dot * o_h_N
+
+    rho_H = ON @ (rd_N - rc_N)
+    rho_deriv_H = ON @ (vd_N - vc_N) - np.cross(ON @ omega_ON_N, rho_H)
+
+    return rho_H, rho_deriv_H
+
+
+def hill2cd(
+    rc_N: np.ndarray, vc_N: np.ndarray, rho_H: np.ndarray, rho_deriv_H: np.ndarray
+) -> Tuple[np.ndarray, np.ndarray]:
+    h_N = np.cross(rc_N, vc_N)
+    o_h_N = h_N / np.linalg.norm(h_N)
+    ON = rv2HN(rc_N, vc_N)
+
+    f_dot = np.linalg.norm(h_N) / np.linalg.norm(rc_N) ** 2
+    omega_ON_N = f_dot * o_h_N
+
+    rd_N = rc_N + ON.T @ rho_H
+    vd_N = vc_N + ON.T @ (rho_deriv_H + np.cross(ON @ omega_ON_N, rho_H))
+
+    return rd_N, vd_N
+
+
 __doc_title__ = "Orbital"
 __all__ = [
+    "random_unit_vector",
     "random_orbit",
     "random_epoch",
     "lla2ecef",
diff --git a/src/bsk_rl/utils/rllib/__init__.py b/src/bsk_rl/utils/rllib/__init__.py
index 1ebb5dc4..5167676d 100644
--- a/src/bsk_rl/utils/rllib/__init__.py
+++ b/src/bsk_rl/utils/rllib/__init__.py
@@ -25,6 +25,7 @@
 
 from bsk_rl import ConstellationTasking, GeneralSatelliteTasking, SatelliteTasking
 from bsk_rl.utils.rllib.callbacks import EpisodeDataParallelWrapper, EpisodeDataWrapper
+from bsk_rl.utils.wrappers import SanitizeNanParallelWrapper, SanitizeNanWrapper
 
 
 def load_torch_mlp_policy(policy_path: str, env: GeneralSatelliteTasking):
@@ -119,7 +120,7 @@ def _satellite_tasking_env_creator(env_config):
         satellite_data_callback = None
 
     return EpisodeDataWrapper(
-        SatelliteTasking(**env_config),
+        SanitizeNanWrapper(SatelliteTasking(**env_config)),
         episode_data_callback=episode_data_callback,
         satellite_data_callback=satellite_data_callback,
     )
@@ -140,7 +141,7 @@ def _constellation_tasking_env_creator(env_config):
 
     return ParallelPettingZooEnv(
         EpisodeDataParallelWrapper(
-            ConstellationTasking(**env_config),
+            SanitizeNanParallelWrapper(ConstellationTasking(**env_config)),
             episode_data_callback=episode_data_callback,
             satellite_data_callback=satellite_data_callback,
         )
diff --git a/src/bsk_rl/utils/rllib/discounting.py b/src/bsk_rl/utils/rllib/discounting.py
index 266b280a..83b64ad4 100644
--- a/src/bsk_rl/utils/rllib/discounting.py
+++ b/src/bsk_rl/utils/rllib/discounting.py
@@ -9,7 +9,7 @@
   :class:`MakeAddedStepActionValid`, and :class:`CondenseMultiStepActions`).
 """
 
-from typing import Any, List, Optional
+from typing import Any, List, Literal, Optional
 
 import numpy as np
 from ray.rllib.algorithms.ppo.ppo_learner import PPOLearner
@@ -116,7 +116,7 @@ def __call__(
             ):
                 last_action = NO_ACTION
                 for action in reversed(episode.actions):
-                    if last_action == NO_ACTION:
+                    if isinstance(action, int) and last_action == NO_ACTION:
                         last_action = action
                     else:
                         break
@@ -233,12 +233,15 @@ def compute_value_targets_time_discounted(
     step_durations,
     gamma: float,
     lambda_: float,
+    reward_time: Literal["step_start", "step_end"] = "step_end",
 ):
     """Computes value function (vf) targets given vf predictions and rewards.
 
     Note that advantages can then easily be computed via the formula:
     advantages = targets - vf_predictions
     """
+    assert reward_time in ["step_start", "step_end"]
+
     # Shift step durations to associate with previous timestep
     # delta_t->t+1 comes with t+1's info, but should be used with t
     step_durations = np.concatenate((step_durations[1:], [step_durations[-1]]))
@@ -248,8 +251,14 @@ def compute_value_targets_time_discounted(
 
     flat_values = np.append(flat_values, 0.0)
     # intermediates = rewards + gamma * (1 - lambda_) * flat_values[1:]
-    # intermediates = rewards + gamma**step_durations * (1 - lambda_) * flat_values[1:]
-    intermediates = gamma**step_durations * (rewards + (1 - lambda_) * flat_values[1:])
+    if reward_time == "step_start":
+        intermediates = (
+            rewards + gamma**step_durations * (1 - lambda_) * flat_values[1:]
+        )
+    elif reward_time == "step_end":
+        intermediates = gamma**step_durations * (
+            rewards + (1 - lambda_) * flat_values[1:]
+        )
     continues = 1.0 - terminateds
 
     Rs = []
@@ -333,6 +342,7 @@ def _compute_gae_from_episodes(
             )
 
             # Compute value targets.
+            reward_time = self.config.learner_config_dict.get("reward_time", "step_end")
             module_value_targets = compute_value_targets_time_discounted(
                 values=module_vf_preds,
                 rewards=unpad_data_if_necessary(
@@ -358,6 +368,7 @@ def _compute_gae_from_episodes(
                 ),
                 gamma=self.config.gamma,
                 lambda_=self.config.lambda_,
+                reward_time=reward_time,
             )
 
             # Remove the extra timesteps again from vf_preds and value targets. Now that
diff --git a/src/bsk_rl/utils/vizard.py b/src/bsk_rl/utils/vizard.py
new file mode 100644
index 00000000..bca2a6dd
--- /dev/null
+++ b/src/bsk_rl/utils/vizard.py
@@ -0,0 +1,52 @@
+"""Utilities for Vizard visualization."""
+
+import inspect
+import logging
+from functools import wraps
+
+logger = logging.getLogger(__name__)
+
+VIZARD_PATH = None
+VIZINSTANCE = None
+
+
+def visualize(func):
+    """Decorator for functions that enable Vizard."""
+
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        if VIZARD_PATH is None:
+            return
+
+        from Basilisk.simulation import vizInterface
+        from Basilisk.utilities import vizSupport
+
+        if not vizSupport.vizFound:
+            logger.warning("Vizard not found, disabling visualization")
+            return
+
+        sig = inspect.signature(func)
+
+        if "vizInstance" in sig.parameters:
+            kwargs["vizInstance"] = VIZINSTANCE
+        if "vizSupport" in sig.parameters:
+            kwargs["vizSupport"] = vizSupport
+        if "vizInterface" in sig.parameters:
+            kwargs["vizInterface"] = vizInterface
+
+        return func(*args, **kwargs)
+
+    return wrapper
+
+
+@visualize
+def get_color(index):
+    from matplotlib.colors import TABLEAU_COLORS
+
+    n_colors = len(TABLEAU_COLORS)
+    color = list(TABLEAU_COLORS.keys())[index % n_colors]
+    return color
+
+
+__doc_title__ = "Vizard"
+__all__ = ["visualize", "VIZARD_PATH"]
diff --git a/src/bsk_rl/utils/wrappers.py b/src/bsk_rl/utils/wrappers.py
new file mode 100644
index 00000000..e52a6413
--- /dev/null
+++ b/src/bsk_rl/utils/wrappers.py
@@ -0,0 +1,56 @@
+import logging
+
+import numpy as np
+from gymnasium import Wrapper
+from pettingzoo.utils import BaseParallelWrapper
+
+logger = logging.getLogger(__name__)
+
+
+def sanitize_nan(value, replace_with=0, warn=True):
+    """Replace NaN values with a given value."""
+    recast_to_list = False
+    if isinstance(value, list):
+        recast_to_list = True
+        value = np.array(value)
+
+    if isinstance(value, np.ndarray):
+        if warn and np.isnan(value).any():
+            logger.warning(
+                f"Replacing NaN values in array with {replace_with}. Array: {value}"
+            )
+        value[np.isnan(value)] = replace_with
+    elif isinstance(value, dict):
+        for key, val in value.items():
+            value[key] = sanitize_nan(val, replace_with)
+    elif isinstance(value, tuple):
+        value = tuple(sanitize_nan(val, replace_with) for val in value)
+
+    if recast_to_list:
+        value = value.tolist()
+
+    return value
+
+
+class SanitizeNanBaseWrapper:
+    def reset(self, **kwargs):
+        observation, info = self.env.reset(**kwargs)
+        observation = sanitize_nan(observation)
+        return observation, info
+
+    def step(self, action):
+        observation, reward, terminated, truncated, info = self.env.step(action)
+        observation = sanitize_nan(observation)
+        return observation, reward, terminated, truncated, info
+
+
+class SanitizeNanWrapper(SanitizeNanBaseWrapper, Wrapper):
+    def __init__(self, env):
+        SanitizeNanBaseWrapper.__init__(self)
+        Wrapper.__init__(self, env)
+
+
+class SanitizeNanParallelWrapper(SanitizeNanBaseWrapper, BaseParallelWrapper):
+    def __init__(self, env):
+        SanitizeNanBaseWrapper.__init__(self)
+        BaseParallelWrapper.__init__(self, env)
diff --git a/tests/integration/data/test_int_data.py b/tests/integration/data/test_int_data.py
index f652899e..96f1d4d2 100644
--- a/tests/integration/data/test_int_data.py
+++ b/tests/integration/data/test_int_data.py
@@ -1,5 +1,57 @@
+import gymnasium as gym
+
+from bsk_rl import act, data, obs, sats, scene
+from bsk_rl.data.composition import ComposedReward
+from bsk_rl.utils.orbital import random_orbit
+
 # For data models not tested in other tests
 
 # NoData sufficiently checked in many cases
 
 # UniqueImageData sufficiently checked in test_int_communication
+
+# from ..test_int_full_environments
+
+
+class FullFeaturedSatellite(sats.ImagingSatellite):
+    observation_spec = [
+        obs.SatProperties(dict(prop="r_BN_P", module="dynamics", norm=6e6)),
+        obs.Time(),
+    ]
+    action_spec = [act.Image(n_ahead_image=10)]
+
+
+def test_multi_rewarder():
+    env = gym.make(
+        "GeneralSatelliteTasking-v1",
+        satellites=[
+            FullFeaturedSatellite(
+                "Sentinel-2A",
+                sat_args=FullFeaturedSatellite.default_sat_args(
+                    oe=random_orbit,
+                    imageAttErrorRequirement=0.01,
+                    imageRateErrorRequirement=0.01,
+                ),
+            ),
+            FullFeaturedSatellite(
+                "Sentinel-2B",
+                sat_args=FullFeaturedSatellite.default_sat_args(
+                    oe=random_orbit,
+                    imageAttErrorRequirement=0.01,
+                    imageRateErrorRequirement=0.01,
+                ),
+            ),
+        ],
+        scenario=scene.UniformTargets(n_targets=1000),
+        rewarder=(data.UniqueImageReward(), data.UniqueImageReward()),
+        sim_rate=0.5,
+        max_step_duration=1e9,
+        time_limit=5700.0,
+        disable_env_checker=True,
+    )
+
+    assert isinstance(env.unwrapped.rewarder, ComposedReward)
+
+    env.reset()
+    for _ in range(10):
+        env.step(env.action_space.sample())
diff --git a/tests/unittest/data/test_composition.py b/tests/unittest/data/test_composition.py
new file mode 100644
index 00000000..0ec7b5fb
--- /dev/null
+++ b/tests/unittest/data/test_composition.py
@@ -0,0 +1,157 @@
+from unittest.mock import MagicMock
+
+import pytest
+
+from bsk_rl.data.composition import ComposedData, ComposedDataStore, ComposedReward
+
+
+class TestComposedData:
+    @pytest.mark.parametrize(
+        "data1, data2, expected",
+        [
+            ((1, 2), (3, 4), (4, 6)),
+            ((), (3, 4), (3, 4)),
+            ((1, 2), (), (1, 2)),
+            ((), (), ()),
+        ],
+    )
+    def test_add(self, data1, data2, expected):
+        composed_data = ComposedData(*data1)
+        other_composed_data = ComposedData(*data2)
+        result = composed_data + other_composed_data
+        assert result.data == expected
+
+    def test_add_different_lengths(self):
+        composed_data = ComposedData(1, 2)
+        other_composed_data = ComposedData(3)
+        with pytest.raises(ValueError):
+            composed_data + other_composed_data
+
+    def test_getattr(self):
+        data1 = MagicMock()
+        data1.a = 1
+        del data1.b
+        del data1.c
+        data2 = MagicMock()
+        data2.b = 2
+        del data2.a
+        del data2.c
+        composed_data = ComposedData(data1, data2)
+        assert composed_data.a == 1
+        assert composed_data.b == 2
+        with pytest.raises(AttributeError):
+            _ = composed_data.c
+
+
+class TestComposedDataStore:
+    def test_pass_data(self):
+        sat = MagicMock()
+        ds1 = MagicMock()
+        ds1_type = MagicMock(return_value=ds1)
+        ds2 = MagicMock()
+        ds2_type = MagicMock(return_value=ds2)
+        composed_data_store = ComposedDataStore(sat, ds1_type, ds2_type)
+        composed_data_store.data = ComposedData(1, 2)
+        composed_data_store.pass_data()
+        assert ds1.data == 1
+        assert ds2.data == 2
+
+    def test_getattr(self):
+        sat = MagicMock()
+        ds1 = MagicMock()
+        ds1_type = MagicMock(return_value=ds1)
+        ds2 = MagicMock()
+        ds2_type = MagicMock(return_value=ds2)
+        composed_data_store = ComposedDataStore(sat, ds1_type, ds2_type)
+        ds1.a = 1
+        assert composed_data_store.a == 1
+
+    def test_get_log_state(self):
+        sat = MagicMock()
+        ds1 = MagicMock(get_log_state=MagicMock(return_value=1))
+        ds1_type = MagicMock(return_value=ds1)
+        ds2 = MagicMock(get_log_state=MagicMock(return_value=2))
+        ds2_type = MagicMock(return_value=ds2)
+        composed_data_store = ComposedDataStore(sat, ds1_type, ds2_type)
+
+        log_states = composed_data_store.get_log_state()
+        for ds in [ds1, ds2]:
+            ds.get_log_state.assert_called_once()
+        assert log_states == [1, 2]
+
+    def test_compare_log_states(self):
+        sat = MagicMock()
+        ds1 = MagicMock(get_log_state=MagicMock(return_value=1))
+        ds1_type = MagicMock(return_value=ds1)
+        ds2 = MagicMock(get_log_state=MagicMock(return_value=2))
+        ds2_type = MagicMock(return_value=ds2)
+        composed_data_store = ComposedDataStore(sat, ds1_type, ds2_type)
+
+        composed_data_store.compare_log_states([1, 2], [3, 4])
+        ds1.compare_log_states.assert_called_once_with(1, 3)
+        ds2.compare_log_states.assert_called_once_with(2, 4)
+
+
+class TestComposedReward:
+    def test_pass_data(self):
+        rewarder1 = MagicMock()
+        rewarder2 = MagicMock()
+        composed_rewarder = ComposedReward(rewarder1, rewarder2)
+        composed_rewarder.data = ComposedData(1, 2)
+        composed_rewarder.pass_data()
+        assert rewarder1.data == 1
+        assert rewarder2.data == 2
+
+    @pytest.mark.parametrize(
+        "function",
+        [
+            "reset_pre_sim_init",
+            "reset_during_sim_init",
+            "reset_post_sim_init",
+            "reset_overwrite_previous",
+        ],
+    )
+    def test_resetable(self, function):
+        rewarder1 = MagicMock()
+        rewarder2 = MagicMock()
+        composed_rewarder = ComposedReward(rewarder1, rewarder2)
+        getattr(composed_rewarder, function)()
+        for rewarder in [rewarder1, rewarder2]:
+            getattr(rewarder, function).assert_called_once()
+
+    def test_initial_data(self):
+        rewarder1 = MagicMock(initial_data=MagicMock(return_value=1))
+        rewarder2 = MagicMock(initial_data=MagicMock(return_value=2))
+        composed_rewarder = ComposedReward(rewarder1, rewarder2)
+        data = composed_rewarder.initial_data("sat")
+        assert data.data == (1, 2)
+
+    def test_data_store(self):
+        sat = MagicMock()
+        ds1 = MagicMock(get_log_state=MagicMock(return_value=1))
+        ds1_type = MagicMock(return_value=ds1)
+        rewarder1 = MagicMock(datastore_type=ds1_type)
+        ds2 = MagicMock(get_log_state=MagicMock(return_value=2))
+        ds2_type = MagicMock(return_value=ds2)
+        rewarder2 = MagicMock(datastore_type=ds2_type)
+        composed_rewarder = ComposedReward(rewarder1, rewarder2)
+        composed_rewarder.create_data_store(sat)
+        assert sat.data_store.datastores == (ds1, ds2)
+
+    def test_calculate_reward(self):
+        rewarder1 = MagicMock(
+            calculate_reward=MagicMock(return_value={"sat1": 1, "sat2": 2})
+        )
+        rewarder2 = MagicMock(
+            calculate_reward=MagicMock(return_value={"sat1": 3, "sat2": 4})
+        )
+        composed_rewarder = ComposedReward(rewarder1, rewarder2)
+
+        reward = composed_rewarder.calculate_reward(
+            {
+                "sat1": MagicMock(data=["d11", "d21"]),
+                "sat2": MagicMock(data=["d12", "d22"]),
+            }
+        )
+
+        assert reward == {"sat1": 4, "sat2": 6}
diff --git a/tests/unittest/test_gym_env.py b/tests/unittest/test_gym_env.py
index 91744701..04584c02 100644
--- a/tests/unittest/test_gym_env.py
+++ b/tests/unittest/test_gym_env.py
@@ -4,6 +4,7 @@
 from gymnasium import spaces
 
 from bsk_rl import ConstellationTasking, GeneralSatelliteTasking, SatelliteTasking
+from bsk_rl.data.composition import ComposedReward
 from bsk_rl.sats import Satellite
 
 
@@ -68,6 +69,18 @@ def test_minimum_world_model_mixed(self):
         assert issubclass(model, TypeA)
         assert issubclass(model, TypeB)
 
+    def test_multiple_rewarders(self):
+        mock_sat = MagicMock()
+        mock_sat.sat_args_generator = {}
+        mock_rewarder = [MagicMock(scenario=None), MagicMock(scenario=None)]
+        env = GeneralSatelliteTasking(
+            satellites=[mock_sat],
+            world_type=MagicMock(),
+            scenario=MagicMock(),
+            rewarder=mock_rewarder,
+        )
+        assert isinstance(env.rewarder, ComposedReward)
+
     @patch("bsk_rl.gym.Simulator")
     def test_reset(self, mock_sim):
         mock_sat = MagicMock()