| {"mean_reward": -0.18840148211456836, "std_reward": 0.11407840663614473, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-06T02:47:54.695783"} |
| {"mean_reward": -0.18840148211456836, "std_reward": 0.11407840663614473, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-06T02:47:54.695783"} |