HumanCompatibleAI / overcooked_ai

A benchmark environment for fully cooperative human-AI performance.

https://arxiv.org/abs/1910.05789

MIT License

683 stars 144 forks source link

Base gym rendering implementation #126

Closed wduguay-air closed 1 year ago

wduguay-air commented 1 year ago

Description

Added a base gym rendering method. Render return format: RGB array. The visualization was tested with a third party RLHF framework called Cogment-Verse (github).

Cogment-Verse is currently setup to install a fork of this repository with the suggested change. See this doc for instructions.

Type of change

[ ] Bug fix (non-breaking change which fixes an issue)
[x] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
[ ] This change requires a documentation update

Checklist:

[x] I have commented my code, particularly in hard-to-understand areas
[x] I have made corresponding changes to the documentation
[x] My changes generate no new warnings
[x] I have added tests that prove my fix is effective or that my feature works

micahcarroll commented 1 year ago

Thanks @wduguay-air! If you can get the final checks passing that would be great:

The exact linting commands can be found in the github actions script and here.
Probably the changes require adding cv to the requirements in setup.py

wduguay-air commented 1 year ago

Ran linters, updated setup.py for opencv-python. Having all sorts of environment issues when running tests locally.

wduguay-air commented 1 year ago

Could you approve the workflows?

micahcarroll commented 1 year ago

Yes, sorry I missed the previous message!

wduguay-air commented 1 year ago

I didn't have the right black version. Linters now fixed. Workflows should pass now.

codecov[bot] commented 1 year ago

Codecov Report

Merging #126 (6f0865a) into master (a12aebb) will decrease coverage by 0.18%. The diff coverage is n/a.

@@            Coverage Diff             @@
##           master     #126      +/-   ##
==========================================
- Coverage   82.44%   82.26%   -0.18%     
==========================================
  Files          16       16              
  Lines        3759     3773      +14     
==========================================
+ Hits         3099     3104       +5     
- Misses        660      669       +9

see 1 file with indirect coverage changes

:mega: We’re building smart automated test selection to slash your CI/CD build times. Learn more

micahcarroll commented 1 year ago

Thanks so much @wduguay-air!! Appreciate you making the PR and following up! Sorry for my slow response!