{"mean_reward": -0.20905363122001291, "std_reward": 0.10217928277947298, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-05T17:01:37.043716"} |
{"mean_reward": -0.20905363122001291, "std_reward": 0.10217928277947298, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-05T17:01:37.043716"} |