| {"mean_reward": 655.5, "std_reward": 222.50224717966333, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-10T19:29:07.958935"} |
| {"mean_reward": 655.5, "std_reward": 222.50224717966333, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-10T19:29:07.958935"} |