New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Doubt on Action Space #36

Open

FailedMesh opened this issue May 3, 2023 · 1 comment

FailedMesh commented May 3, 2023

A single sample in the D4RL Maze2D environment is of dimension (384, 6)
Can you please clarify the below 2 questions:

Does the second dimension (6) have an ordering of state followed by action ,or ,action followed by state?
If the state is (qpos, qvel) it already has the position and velocity information, then what information does the action represent?

Owner

jannerm commented Jun 7, 2023

The actions precede observations in the trajectories (here is the line where they are concatenated).
The applied actions are forces. Here is the MazeEnv definition from D4RL, which you can follow upstream to the MujocoEnv class from mujoco-py, if you would like to take a look at some of the (python-wrapped) simulation code.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment