| {"mean_reward": 730.5, "std_reward": 256.0805537326097, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-22T21:25:42.508742"} |
| {"mean_reward": 730.5, "std_reward": 256.0805537326097, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-22T21:25:42.508742"} |