dm_control
dm_control copied to clipboard
google-deepmind
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Previously, the test was only checking the first timestep returned by the environment and not subsequent timesteps generated by the trajectory rollout.
This PR addresses #211.
Hi, I have an environment where the robot needs to reach different goal positions that are randomized at every timestep. I am representing the goal as a site on the...
We would like to simulate a custom robotic manipulation task environment and then use it in a reinforcement learning framework. It is possible to use dm_control components to do that...
Using the latest install for both dm_control and mujoco via pypi, the viewer can not render a window on OSX (intel chip). Script: ``` from dm_control import suite from dm_control...
Hi~ Thanks for your great work. I am playing with the locomotion soccer environment. But I have no idea about the meaning of some observation variables: They look like the...
I am trying to train a 1v1 soccer games in the soccer environment. However, the training is really slow. Is there any method to speed up the simulation?
I enjoy this library and have used it in research , I'm currently writing my graduate paper, where i'll be showing my benchmark for the rgb stacking problem. Looking through...
Is there a recommend way to single step the viewer renderer? In the example code snippet, I would like to grab input (ex: keyboard presses for direction) and update viewer...
The vision environment provide only RGB images, instead of RGBD (depth) images, but I see some partial implementation of depth images. Here's my attempt to set `depth=True`, but it failes...
Metadata
Owner
Metadata
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.