| {"mean_reward": 533.0, "std_reward": 171.72943836162744, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-10T15:35:04.771000"} |
| {"mean_reward": 533.0, "std_reward": 171.72943836162744, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-10T15:35:04.771000"} |