{"mean_reward": -0.2819627326913178, "std_reward": 0.17091621116559005, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-08T21:40:36.381934"} |
{"mean_reward": -0.2819627326913178, "std_reward": 0.17091621116559005, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-08T21:40:36.381934"} |