{"mean_reward": 598.0, "std_reward": 107.38249391777042, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-10T12:00:06.415603"} |
{"mean_reward": 598.0, "std_reward": 107.38249391777042, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-10T12:00:06.415603"} |