| {"mean_reward": 518.0, "std_reward": 237.9831926838532, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-10T07:17:37.991186"} |
| {"mean_reward": 518.0, "std_reward": 237.9831926838532, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-10T07:17:37.991186"} |