| {"mean_reward": 473.0, "std_reward": 176.8078052575734, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-11-21T13:14:05.405363"} |
| {"mean_reward": 473.0, "std_reward": 176.8078052575734, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-11-21T13:14:05.405363"} |