| {"mean_reward": 501.5, "std_reward": 260.0773923277454, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-28T00:06:03.953242"} |
| {"mean_reward": 501.5, "std_reward": 260.0773923277454, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-28T00:06:03.953242"} |