{"mean_reward": -0.21022119875997305, "std_reward": 0.12101208170477012, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-29T14:55:58.428820"} |
{"mean_reward": -0.21022119875997305, "std_reward": 0.12101208170477012, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-29T14:55:58.428820"} |