{"mean_reward": 931.5, "std_reward": 414.82556575023193, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-16T16:08:29.220037"} |
{"mean_reward": 931.5, "std_reward": 414.82556575023193, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-16T16:08:29.220037"} |