| {"mean_reward": 720.5, "std_reward": 166.0489385693266, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-29T09:27:10.657973"} |
| {"mean_reward": 720.5, "std_reward": 166.0489385693266, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-29T09:27:10.657973"} |