{"mean_reward": -0.253515622485429, "std_reward": 0.07785978420180033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-30T14:05:34.827777"} |
{"mean_reward": -0.253515622485429, "std_reward": 0.07785978420180033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-30T14:05:34.827777"} |