| {"mean_reward": 538.5, "std_reward": 119.3534666442496, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T08:47:58.950469"} |
| {"mean_reward": 538.5, "std_reward": 119.3534666442496, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T08:47:58.950469"} |