| {"mean_reward": 555.0, "std_reward": 139.17614738165446, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-22T20:39:54.241767"} |
| {"mean_reward": 555.0, "std_reward": 139.17614738165446, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-22T20:39:54.241767"} |