diff --git a/.buildinfo b/.buildinfo index 57d3eeb..5d3621c 100644 --- a/.buildinfo +++ b/.buildinfo @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: 9986bfe18e50103f262e6e0f780db79b +config: cdc3ee0c0ca9856489cceb64ac6b5cbb tags: d77d1c0d9ca2f4c8421862c7c5a0d620 diff --git a/404.html b/404.html index 92acacc..372d682 100644 --- a/404.html +++ b/404.html @@ -252,7 +252,6 @@
See https://gymnasium.farama.org/main/environments/mujoco/walker2d/#version-history
Continuous / Discrete
[target_1, target_2, target_3, target_4]
Mujoco version of mo-reacher-v0
, based on Reacher-v4
environment.
Multi-objective version of Reacher-v5
environment.
Continuous / Continuous
[velocity, height, energy]
Multi-objective version of Hopper-v4 env.
Multi-objective version of Hopper-v5 env.
Continuous / Continuous
[velocity, energy]
Multi-objective version of HalfCheetah-v4 env. Similar to Xu et al. 2020.
Multi-objective version of HalfCheetah-v5 env. Similar to Xu et al. 2020.
Continuous / Continuous
[velocity, energy]
Multi-objective version of Walker2d-v4 env.
Multi-objective version of Walker2d-v5 env.
Continuous / Continuous
[x_velocity, y_velocity, energy]
Multi-objective version of Ant-v4 env.
Multi-objective version of Ant-v5 env.
Continuous / Continuous
[velocity, energy]
Multi-objective version of Swimmer-v4 env.
Multi-objective version of Swimmer-v5 env.
Continuous / Continuous
[velocity, energy]
Multi-objective version of Humonoid-v4 env.
Multi-objective version of Humonoid-v5 env.
Released on 2024-10-28 - GitHub - PyPI
+Doc fixes
+Full Changelog: v1.3.0...v1.3.1
Released on 2024-10-28 - GitHub - PyPI
@@ -462,7 +466,7 @@With MORL, users have the flexibility to determine the compromises they desire based on their preferences for each objective. Consequently, the environments in MO-Gymnasium do not have predefined weights. Thus, MO-Gymnasium extends the capabilities of Gymnasium to the multi-objective setting, where the agents receives a vectorial reward.
For example, here is an illustration of the multiple policies learned by an MORL agent for the mo-halfcheetah
domain, balancing between saving battery and speed:
This release marks the first mature version of MO-Gymnasium within Farama, indicating that the API is stable, and we have achieved a high level of quality in this library.
MORecordEpisode
-
+
diff --git a/wrappers/wrappers/index.html b/wrappers/wrappers/index.html
index 444ce2c..701e582 100644
--- a/wrappers/wrappers/index.html
+++ b/wrappers/wrappers/index.html
@@ -252,7 +252,6 @@
- MO-Hopper
- MO-Halfcheetah
- MO-Walker2D
-- Version History
- MO-Ant
- MO-Swimmer
- MO-Humanoid
@@ -527,7 +526,7 @@ MOMaxAndSkipObs
-
+