{"mean_reward": -0.206029608938843, "std_reward": 0.1103435162875929, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-07T03:39:35.414039"} |
{"mean_reward": -0.206029608938843, "std_reward": 0.1103435162875929, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-07T03:39:35.414039"} |