| {"mean_reward": -0.21912028063088657, "std_reward": 0.10116075553498993, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-13T16:08:02.074629"} |
| {"mean_reward": -0.21912028063088657, "std_reward": 0.10116075553498993, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-13T16:08:02.074629"} |