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: term vs trunc #983

Open sash-a opened 8 months ago

sash-a commented 8 months ago

Note

This is quite confusing so please check this carefully and make sure I haven't mixed up where to use each one!

What?

Mostly explained in #951. We are mixing up termination and truncation. This is especially prevalent in recurrent systems, but all systems have this issue.

Now very explicit about termination vs truncation, removed all mentions of done. Done attribute remove from RnnLearnerState and replaced with truncated in the PpoTransition.

How?

Explicitly name variables termination and trunctation instead of done