| {"mean_reward": 516.0, "std_reward": 168.59418732566078, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-18T09:06:19.832823"} |
| {"mean_reward": 516.0, "std_reward": 168.59418732566078, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-18T09:06:19.832823"} |