NathanGavenski/HalfCheetah-v4
收藏Hugging Face2024-11-21 更新2024-12-14 收录
下载链接：
https://hf-mirror.com/datasets/NathanGavenski/HalfCheetah-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9809.9417。每个条目包含观察值、动作、奖励和episode开始标志。
The dataset consists of 1,000 episodes with an average episodic reward of `9809.9417`. Each entry consists of:
- obs (list): observation with length 2.
- action (int): action (0 or1).
- reward (float): reward point for that timestep.
- episode_starts (bool): if that state was the initial timestep for an episode.
The dataset can be freely downloaded and used, and there is a PyTorch Dataset implementation that allows for more control, such as train and test splits and the number of episodes used.
提供机构：
NathanGavenski
