| {"mean_reward": 591.0, "std_reward": 142.66744548074027, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-28T21:33:04.689008"} |
| {"mean_reward": 591.0, "std_reward": 142.66744548074027, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-28T21:33:04.689008"} |