{"mean_reward": 678.5, "std_reward": 122.41425570577962, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-11-06T16:45:28.487652"} |
{"mean_reward": 678.5, "std_reward": 122.41425570577962, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-11-06T16:45:28.487652"} |