| {"mean_reward": 609.0, "std_reward": 97.7957054271812, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-04-01T18:56:55.621265"} |
| {"mean_reward": 609.0, "std_reward": 97.7957054271812, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-04-01T18:56:55.621265"} |