| {"mean_reward": 256.3823095992744, "std_reward": 17.509715534720705, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T23:36:52.911978"} |
| {"mean_reward": 256.3823095992744, "std_reward": 17.509715534720705, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T23:36:52.911978"} |