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: Edit JaxMARL wrapper #1019

Closed WiemKhlifi closed 7 months ago

WiemKhlifi commented 7 months ago

What?

Edit the JaxMARL wrapper to support the mabrax environment.

Why?

These changes serve to support mabrax and use the brax's observation as the global state for the mappo systems. These changes are useful for the continuous actions PR #1000.