| {"mean_reward": 256.86992603796693, "std_reward": 21.587462337270033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-12T08:54:12.251834"} |
| {"mean_reward": 256.86992603796693, "std_reward": 21.587462337270033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-12T08:54:12.251834"} |