From here , I learned that the “episode_reward_mean” metric indicates the average of rewards collected in all previous episodes. How can I obtain a single episode reward? Should I make a custom metric for it in the callback class?

If you look at your progress.csv files in ~/ray_results you can see that it already saves the individual episode rewards in “hist_stat/episode_reward”, if you have the train_results (like ray/action_masking.py at a7d552ca2541376b87a40bc6b2189bab5a5c6c5a · ray-project/ray · GitHub ) as a variable then…

How to obtain single episode reward?

RLlib

Erica March 19, 2024, 9:58am 7

For other people with this question that may end up here. I found the answer here: Accessing custom metrics for episodes - #2 by cool-RR

Topic		Replies	Views
Custom Tensorboard Metric (episode.total_reward auto generates as mean, min, max) RLlib	5	138	June 24, 2024
RLlib callbacks to get custom metrics such as observation, reward...etc in each episode from SingleAgentEpisode and access it in the trainer RLlib	1	21	November 14, 2024
Mean reward per agent in MARL RLlib	11	1047	January 12, 2023
Can ray allow access to individual episodes? RLlib	5	440	September 22, 2021
Custom metrics only mean value RLlib	3	850	February 16, 2022

How to obtain single episode reward?

Related topics