{"mean_reward": 9.2, "std_reward": 0.4, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-27T22:18:14.967691"} |
{"mean_reward": 9.2, "std_reward": 0.4, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-27T22:18:14.967691"} |