| {"mean_reward": 251.1242375614398, "std_reward": 14.559071890674872, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T04:37:27.946506"} |
| {"mean_reward": 251.1242375614398, "std_reward": 14.559071890674872, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T04:37:27.946506"} |