Open Ericonaldo opened 2 years ago
Would you like to provide an example (just a link) to show the common-style dm_control usage?
https://github.com/MishaLaskin/rad/blob/18d079e677398c70ff2eefefcc81d5a99662103d/train.py#L207
RAD. The current SoTA RL algorithm on DMC.
Motivation
DMC experiments always need a framestack wrapper. However it is hard to implement it out of envpool because we should wrap env before creating vector envs.
Solution
Can you explain why, and whether it is possible to support this wrapper?
Checklist