task.xml

<mujoco model="Acrobot Swing-Up">
  <include file="../common.xml"/>
  <!-- modified from: https://github.com/google-deepmind/dm_control/blob/main/dm_control/suite/acrobot.xml-->
  <include file="acrobot_modified.xml" />

  <size memory="4K"/>

  <custom>
    <numeric name="agent_planner" data="0" />
    <numeric name="agent_horizon" data="2.0" />
    <numeric name="agent_timestep" data="0.01" />
    <numeric name="sampling_sample_width" data="0.01" />
    <numeric name="sampling_control_width" data="0.015" />
    <numeric name="sampling_spline_points" data="10" />
    <numeric name="sampling_exploration" data="0.05" />
    <numeric name="gradient_spline_points" data="10" />
    <numeric name="residual_Goal" data="0 -1.5 1.5" />
  </custom>

  <sensor>
    <user name="Distance" dim="2" user="0 50.0 0 100.0"/>
    <user name="Velocity" dim="2" user="0  1.0 0 10.0"/>
    <user name="Control" dim="1" user="0 0.05 0.0 1.0"/>
    <framepos name="trace0" objtype="site" objname="tip"/>
    <framepos name="position" objtype="site" objname="tip"/>
    <framelinvel name="velocity" objtype="site" objname="tip"/>
  </sensor>

  <keyframe>
  <!-- Start from bottom position. -->
  <key name="home" qpos="3.142 0"/>
  </keyframe>
</mujoco>