| {"mean_reward": -9.7, "std_reward": 4.172529209005013, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-16T17:27:00.041297"} |
| {"mean_reward": -9.7, "std_reward": 4.172529209005013, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-16T17:27:00.041297"} |