{"mean_reward": -0.18618006240576507, "std_reward": 0.09189833643517539, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-18T22:33:51.698011"} |
{"mean_reward": -0.18618006240576507, "std_reward": 0.09189833643517539, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-18T22:33:51.698011"} |