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: RL baselines as policy support #60

Draft
wants to merge 24 commits into
base: main
Choose a base branch
from

Conversation

KornbergFresnel
Copy link
Member

Add more RL algorithms as baselines

@KornbergFresnel KornbergFresnel linked an issue Feb 28, 2023 that may be closed by this pull request
@KornbergFresnel KornbergFresnel marked this pull request as draft February 28, 2023 04:38
@codecov
Copy link

codecov bot commented Apr 7, 2023

Codecov Report

Attention: 90 lines in your changes are missing coverage. Please review.

Comparison is base (79562dd) 89.99% compared to head (e736658) 86.76%.
Report is 3 commits behind head on main.

❗ Current head e736658 differs from pull request most recent head 030407c. Consider uploading reports for the commit 030407c to get more accurate results

Files Patch % Lines
malib/common/vtrace.py 0.00% 46 Missing ⚠️
malib/rl/ppo/trainer.py 14.00% 43 Missing ⚠️
malib/rl/ppo/policy.py 87.50% 1 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main      #60      +/-   ##
==========================================
- Coverage   89.99%   86.76%   -3.23%     
==========================================
  Files          36       40       +4     
  Lines        2338     2441     +103     
==========================================
+ Hits         2104     2118      +14     
- Misses        234      323      +89     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

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.

How to use PPO to train in psro_scenario
1 participant