| {"mean_reward": 662.0, "std_reward": 175.7156794369814, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T08:16:52.395079"} |
| {"mean_reward": 662.0, "std_reward": 175.7156794369814, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T08:16:52.395079"} |