dm_control
dm_control copied to clipboard
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
How could I use the [2020 humanoid_CMU torques, kp and damping values](https://github.com/deepmind/dm_control/blob/4e1a35595124742015ae0c7a829e099a5aa100f5/dm_control/locomotion/walkers/cmu_humanoid.py#L423) for the [Humanoid_CMU](https://github.com/deepmind/dm_control/blob/main/dm_control/suite/humanoid_CMU.py#L108) stand, walk and run tasks? Is there any way to do this that wouldn't require...
[Tassa et al., 2020, page 25, third paragraph from bottom](https://arxiv.org/abs/2006.12983) describes the Humanoid_CMU domain as having the `stand`, `walk` and `run` tasks -- however the `walk` task is missing.
As per title
The various `plugin` elements have a name attribute defined in [schema.xml](https://github.com/google-deepmind/dm_control/blob/main/dm_control/mjcf/schema.xml) of the mjcf module. However, some plugins like body plugins do not have a name in `mujoco`. Because `dm_control`...
Mujoco 3.0 introduced [flexcomp](https://mujoco.readthedocs.io/en/stable/XMLreference.html#body-flexcomp) object for modelling deformable obejcts. However trying to create a Prop using ```python class Cloth(prop.Prop): """Simple cloth prop that consists of a MuJoco flexcomp.""" def _build(self,...
Hi, I am a student trying to use the [humanoid_CMU](https://github.com/google-deepmind/dm_control/blob/main/dm_control/suite/humanoid_CMU.xml). I have the mocap data from CMU website in the form of an .amc file. How can I use these...
I have updated the inverse kinematics script to support multiple sites. It still supports the previous script and all the tests run correctly. There is also a new visualise script...
I get the following errors while following the documentation. `ValueError: Expect keyword to be one of ['radian', 'degree'] but got: radians` This PR updates the readme file.
I'm getting this error while using the EGL rendering backend: `mujoco.FatalError: Offscreen framebuffer is not complete, error 0x8cdd` The error is rare (but still fatal for a long job) so...
Is it a known issue that soccer and humanoid examples are not working in dm_control colab: https://colab.research.google.com/github/google-deepmind/dm_control/blob/main/tutorial.ipynb? 