google-deepmind / google-deepmind/dm_control

Rendering the viewer with substeps (aka. physical timestep) instead of steps (aka. control timestep)

Open
#400 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
4.7k
Forks
764
PR merge metrics
No merged PRs in 30d

Description

I made my own task in dm_control, but unfortunately, the action of my task is not only the actuator control values but also an unfixed control duration. For every control step, my agent will decide how long this control period is, and the time vary from 0.02 to 0.1 seconds (the details are just setting the timestep before every step).

I would like to render my dm_control env under the 'viewer' module your package provided.

How can I implement it in this situation?

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.