NathanGavenski/Ant-v4
收藏Hugging Face2024-11-26 更新2024-12-14 收录
下载链接：
https://hf-mirror.com/datasets/NathanGavenski/Ant-v4
下载链接
链接失效反馈官方服务：
资源简介：
该数据集由Imitation Learning Datasets项目创建，使用了来自HuggingFace的TD3策略的Stable Baselines权重。数据集包含1000个episode，每个episode的平均奖励为5913.2959。每个条目包含观察值（长度为27的列表）、动作（0或1）、奖励（浮点数）和episode开始标志（布尔值）。
The dataset consists of 1,000 episodes with an average episodic reward of `5913.2959`. Each entry consists of:
- `obs` (list): observation with length 27.
- `action` (int): action (0 or 1).
- `reward` (float): reward point for that timestep.
- `episode_starts` (bool): if that state was the initial timestep for an episode.
提供机构：
NathanGavenski
