| {"mean_reward": 516.0, "std_reward": 130.78226179417453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-03T12:00:15.231589"} |
| {"mean_reward": 516.0, "std_reward": 130.78226179417453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-03T12:00:15.231589"} |