| {"mean_reward": 642.0, "std_reward": 231.6484405300411, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-03T10:11:34.447492"} |
| {"mean_reward": 642.0, "std_reward": 231.6484405300411, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-03T10:11:34.447492"} |