| {"mean_reward": 535.0, "std_reward": 79.40403012442127, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-24T04:43:03.989720"} |
| {"mean_reward": 535.0, "std_reward": 79.40403012442127, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-24T04:43:03.989720"} |