{"mean_reward": 313.0, "std_reward": 134.6142637315972, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-06T05:23:30.467482"} |
{"mean_reward": 313.0, "std_reward": 134.6142637315972, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-06T05:23:30.467482"} |