{"mean_reward": 256.15552847092675, "std_reward": 22.780058040012367, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-12T12:53:33.629292"} |
{"mean_reward": 256.15552847092675, "std_reward": 22.780058040012367, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-12T12:53:33.629292"} |