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: auto reset wrapper #1017

Closed sash-a closed 7 months ago

sash-a commented 7 months ago

What?

The jumanji auto reset wrapper has a small bug, this is a stop gap PR so that we have access to it until that on is merged: https://github.com/instadeepai/jumanji/pull/223

sash-a commented 7 months ago

Looks good to me @sash-a! Super clean 💪 Is this what you used for your SAC systems?

Yup, hopefully will be in jumanji soon though