| {"mean_reward": -0.18795032501220704, "std_reward": 0.10057652594766689, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-05T05:12:12.323619"} |
| {"mean_reward": -0.18795032501220704, "std_reward": 0.10057652594766689, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-05T05:12:12.323619"} |