{"mean_reward": 428.5, "std_reward": 96.15222306322407, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-23T05:39:58.829857"} |
{"mean_reward": 428.5, "std_reward": 96.15222306322407, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-23T05:39:58.829857"} |