| {"mean_reward": 262.23921137350516, "std_reward": 21.349143006703343, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-20T22:06:32.725818"} |
| {"mean_reward": 262.23921137350516, "std_reward": 21.349143006703343, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-20T22:06:32.725818"} |