{"mean_reward": 430.0, "std_reward": 157.40076238697193, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-09T17:22:12.923786"} |
{"mean_reward": 430.0, "std_reward": 157.40076238697193, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-09T17:22:12.923786"} |