dm_control
dm_control copied to clipboard
google-deepmind
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Hello! As also mentioned in commit 2af59a1, NumPy 1.25 comes with a number of deprecations (https://numpy.org/devdocs/release/1.25.0-notes.html#deprecations). Only ndim-0 arrays are treated as scalars. Conversion of an array with ndim >...
Hi, thank you for releasing the code of this fantastic project! I tried to run the explore.py given in the repo (dm_control/locomotion/soccer/explore.py). However, it seems that the GUI that pops...
This PR adds force sensors to `fruitfly_v2` walker's wings to approximate wing load sensors of the real fruit fly.
What's the difference between the linear velocities in physics.data.sensordata and physics.data.object_velocity? They seem to be different. Thank you for the help.
Hello, whatever the version of dm_control I set I keep getting this errors. ``` env: MUJOCO_GL=egl --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) Cell In[9], line 4 1 get_ipython().run_line_magic('env', 'MUJOCO_GL=egl')...
Hello, I am trying to test if two geoms are in contact. I was thinking of something like physics.named.data."contact" but that is not available. Is there maybe any method of...
Are there pretrained models for the multi-agent soccer, so that the game become fully cooperative (e.g., we only control one team, and the other team loads the pretrained model and...
Right now, the preference order is glfw > egl > osmesa. In the common scenario of training an RL agent on a GPU machine, this means windows will pop up,...
PyMJCF does not support nested include tags the same way as the MuJoCo compiler. No matter how deep the include tag is, MuJoCo expects all included models and their assets...
Metadata
Owner
Metadata
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.