The key is a while loop on the mean_reward variable when evaluating your agent🥰📚

094b889 about 1 year ago

165 Bytes

{"mean_reward": 268.89390700135795, "std_reward": 30.990567156284154, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-12T15:33:56.323331"}