| {"mean_reward": -0.40225191600620747, "std_reward": 0.2572503426260108, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-09T12:50:32.026471"} |
| {"mean_reward": -0.40225191600620747, "std_reward": 0.2572503426260108, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-09T12:50:32.026471"} |