Feat:Sebulba [2] Logger and evaluator - Githubissues

instadeepai / Mava

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

Apache License 2.0

709 stars 83 forks source link

Feat:Sebulba [2] Logger and evaluator #977

Closed OmaymaMahjoub closed 3 months ago

OmaymaMahjoub commented 9 months ago

What?

Implement an evaluator function for sebulba ff systems, and adapt the logger to support this new architecture

Why?

Integrate Sebulba's architecture due to its effectiveness in scenarios involving non-jitted/non-jax environments.

How?

Create additional methods to the logger class and create evaluation function in evaluator.py

Extra

This PR was built on top of #976 and #974 , therefore we need to prioritize closing those PRs first!
In case the reviewer wants to test this code, the full sebulba implementation is now living in feat/sebulba_ff_ippo

OmaymaMahjoub commented 3 months ago

@Louay-Ben-nessir is working on maintaining this PR in a new one that will be added soon :)