[RLLib] Evaluation duration doesn't match with results num episodes for evaluation #46412
Labels
bug
Something that is supposed to be working; but isn't
rllib
RLlib related issues
rllib-evaluation
Bug affecting policy evaluation with RLlib.
rllib-logging
This problem is related to logging metrics
rllib-oldstack-cleanup
Issues related to cleaning up classes, utilities on the old API stack
What happened + What you expected to happen
When using
evaluation_num_env_runners > 1
, for RLLib evaluation, the results["evaluation"]["env_runners"]["num_episodes"]
is not equal to theevaluation_duration
set in the configuration.Versions / Dependencies
Ray 2.31
Python 3.11
Linux
Reproduction script
Issue Severity
Medium: It is a significant difficulty but I can work around it.
The text was updated successfully, but these errors were encountered: