| {"mean_reward": -0.1996128040365875, "std_reward": 0.08450601142375136, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-04T10:16:55.126434"} |
| {"mean_reward": -0.1996128040365875, "std_reward": 0.08450601142375136, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-04T10:16:55.126434"} |