| {"mean_reward": -0.23391641024500132, "std_reward": 0.09931729647116762, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-06T05:17:00.690903"} |
| {"mean_reward": -0.23391641024500132, "std_reward": 0.09931729647116762, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-06T05:17:00.690903"} |