[feature] Mujoco engine - #110
Open
guptadivyansh wants to merge 11 commits into
Open
Conversation
guptadivyansh
marked this pull request as ready for review
May 26, 2026 08:30
Author
|
[Edit] Updated plots with a longer Newton run |
Owner
|
Thanks a lot for putting this PR together! Sorry about the super late response on my part. Have a lot on my plate at the moment. This is a very large change, so I need to find time to go through it in more detail. Just posting this to let you know this is on my radar and I will try to review it as soon as I can. Thanks for your patience! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds mujoco (using warp) as an engine to mimickit. Uses mjlab and
mimickit.engines.newton_engineas references. Iteration speed is almost exactly as fast as the newton implementation but learning is a bit slower (tested on the example humanoid spinkick deepmimic env).Some performance plots are attached but I can also run more tests. Tested on Nvidia RTX 5000 32GB. Log data from the repo is presumably from Isaac Lab and also reflects different hardware. I also tried training on Mujoco and rollout of the learned policy on Newton and the tracking looks subjectively good (and somehow a bit better than the rollout on Mujoco itself).
Disclaimer: mostly written by Codex 5.5 with xHigh thinking, but with a lot of manual iterating, nudging and benchmarking. Happy to iterate more depending on feedback/interest.
solves #100