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

Feature/marl #168

Merged
merged 2 commits into from
Sep 23, 2024
Merged

Feature/marl #168

merged 2 commits into from
Sep 23, 2024

Conversation

Mark2000
Copy link
Contributor

@Mark2000 Mark2000 commented Jul 30, 2024

Description

Closes #184

Adds asynchronous multiagent training utilities for RLlib. Modernizes logging and connectors to work with RLlib 2.35.0 (latest release).

Type of change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)

How should this pull request be reviewed?

  • By commit
  • All changes at once

How Has This Been Tested?

Tests still pass. Connectors and logging are tested in documentation examples.

Passes Tests

  • Unit tests pytest --cov bsk_rl --cov-report term-missing tests/unittest
  • Integrated tests pytest --cov bsk_rl --cov-report term-missing tests/integration
  • Documentation builds cd docs; make html

Test Configuration

  • Python: 3.10.11
  • Basilisk: 2.4
  • Platform: Mac

Checklist:

  • My code follows the style guidelines of this project (passes Black, ruff, and isort)
  • I have performed a self-review of my code
  • I have commented my code in hard-to-understand areas
  • I have made corresponding changes to the documentation and release notes
  • Commit messages are atomic, are in the form Issue #XXX: Message and have a useful message
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • If I changed an example ipynb, I have locally rebuilt the documentation

@Mark2000 Mark2000 force-pushed the feature/marl branch 2 times, most recently from 6b92a51 to d18ab44 Compare July 30, 2024 23:55
@Mark2000
Copy link
Contributor Author

Mark2000 commented Sep 4, 2024

TODO add example scripts for single and multiagent training. (DONE)

@Mark2000 Mark2000 force-pushed the feature/marl branch 6 times, most recently from 304fe7b to 16d8d85 Compare September 12, 2024 21:44
@Mark2000 Mark2000 marked this pull request as ready for review September 12, 2024 21:45
@Mark2000
Copy link
Contributor Author

Mark2000 commented Sep 18, 2024

TODO add to release notes [done]

Copy link

@Yume27 Yume27 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Those are great example scripts for the new RLlib environment! I ran pytest and all the Jupyter Notebook example scripts. It passed all the tests and the example scripts worked.

@Mark2000 Mark2000 merged commit ac856f7 into develop Sep 23, 2024
4 checks passed
@Mark2000 Mark2000 deleted the feature/marl branch September 23, 2024 17:16
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.

Multiagent RL training support and examples.
2 participants