{"mean_reward": 536.0, "std_reward": 136.2497706420088, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-06T16:03:26.251421"} |
{"mean_reward": 536.0, "std_reward": 136.2497706420088, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-06T16:03:26.251421"} |