| {"mean_reward": 85.005738, "std_reward": 2.525246770575264, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-16T13:29:53.468107"} |
| {"mean_reward": 85.005738, "std_reward": 2.525246770575264, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-16T13:29:53.468107"} |