| {"mean_reward": 565.0, "std_reward": 115.17378173872733, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T10:30:03.747355"} |
| {"mean_reward": 565.0, "std_reward": 115.17378173872733, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T10:30:03.747355"} |