{"mean_reward": -0.19798409417271615, "std_reward": 0.0640542800802231, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-20T18:03:17.105712"} |
{"mean_reward": -0.19798409417271615, "std_reward": 0.0640542800802231, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-20T18:03:17.105712"} |