| {"mean_reward": 615.0, "std_reward": 99.37303457175895, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-04T14:09:21.716871"} |
| {"mean_reward": 615.0, "std_reward": 99.37303457175895, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-04T14:09:21.716871"} |