search

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

fix: sometimes logging 0 episode return #1042

Closed sash-a closed 7 months ago

sash-a commented 7 months ago

What?

We were sometimes logging episode returns when our rollout length was too short to hit the end of an episode. Made sure we don't log these episodes.