| {"mean_reward": 263.0183450578104, "std_reward": 16.772183207860806, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-27T11:03:00.266441"} |
| {"mean_reward": 263.0183450578104, "std_reward": 16.772183207860806, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-27T11:03:00.266441"} |