instadeepai/Mava

[BUG] steps_per_second under-reporting in SAC and IQL

Open

#1,078 opened on 2024年5月13日

GitHub で見る
 (0 comments) (0 reactions) (0 assignees)Python (122 forks)auto 404
buggood first issuehelp wanted

Repository metrics

Stars
 (922 stars)
PR merge metrics
 (PR metrics pending)

説明

Describe the bug

The (originally combined) steps_per_second logging has been separated for now to enforce logging consistencies across Mava systems, enabling downstream aggregate plotting via marl-eval. However, the current steps_per_second logging in the IQL and SAC systems is not a true representation for the learner or the actor. It is not entirely fair to say that we do steps_per_rollout / elapsed _time steps per second in both cases because we are also taking anakin_steps * cfg.system.epochs gradient steps.

コントリビューターガイド