| {"mean_reward": -0.1819120836444199, "std_reward": 0.1256124143769455, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T21:06:31.781063"} |
| {"mean_reward": -0.1819120836444199, "std_reward": 0.1256124143769455, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T21:06:31.781063"} |