| {"mean_reward": 600.0, "std_reward": 258.65034312755125, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-18T07:46:47.174232"} |
| {"mean_reward": 600.0, "std_reward": 258.65034312755125, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-18T07:46:47.174232"} |