Skip to content
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.

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

WIP: Implement CrossQ for continuous actions #473

Closed
wants to merge 4 commits into from

Conversation

noahfarr
Copy link

@noahfarr noahfarr commented Jul 19, 2024

Description

Implementing #463

Types of changes

  • Bug fix
  • New feature
  • New algorithm
  • Documentation

Checklist:

  • I've read the CONTRIBUTION guide (required).
  • I have ensured pre-commit run --all-files passes (required).
  • I have updated the tests accordingly (if applicable).
  • I have updated the documentation and previewed the changes via mkdocs serve.
    • I have explained note-worthy implementation details.
    • I have explained the logged metrics.
    • I have added links to the original paper and related papers.

If you need to run benchmark experiments for a performance-impacting changes:

  • I have contacted @vwxyzjn to obtain access to the openrlbenchmark W&B team.
  • I have used the benchmark utility to submit the tracked experiments to the openrlbenchmark/cleanrl W&B project, optionally with --capture_video.
  • I have performed RLops with python -m openrlbenchmark.rlops.
    • For new feature or bug fix:
      • I have used the RLops utility to understand the performance impact of the changes and confirmed there is no regression.
    • For new algorithm:
      • I have created a table comparing my results against those from reputable sources (i.e., the original paper or other reference implementation).
    • I have added the learning curves generated by the python -m openrlbenchmark.rlops utility to the documentation.
    • I have added links to the tracked experiments in W&B, generated by python -m openrlbenchmark.rlops ....your_args... --report, to the documentation.

Copy link

vercel bot commented Jul 19, 2024

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
cleanrl ✅ Ready (Inspect) Visit Preview 💬 Add feedback Jul 19, 2024 0:44am

@pseudo-rnd-thoughts
Copy link
Collaborator

It might be helpful to include within the documentation that for environments with sparse rewards, BatchNorm has been proven to be myopic and not able to learn long time horizon rewards / goals.
Therefore, for MuJoCo, BatchNorm doesn't have a significant negative impact but for Atari and the like, this might.
See https://arxiv.org/pdf/2407.04811, Sections 3.1 and 5.1 + Appendix G

@noahfarr noahfarr closed this by deleting the head repository Aug 27, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants