yusenluo9z/orange_cup_iql_mixed_differential

该数据集是使用LeRobot创建的，主要用于机器人学习任务。数据集包含多种特征，如动作、观察、时间戳和奖励等。具体包括12个浮点型动作特征（如左右肩、肘、腕和夹持器的位置）、观察状态（同样包含12个浮点型特征）、顶部和侧面的视频观察（480x640分辨率，3通道，30fps）、时间戳、帧索引、任务索引等。数据集总共有50个episodes，20894帧，分为2个任务，数据文件大小为100MB，视频文件大小为200MB。

This dataset was created using LeRobot and is primarily used for robot learning tasks. It includes various features such as actions, observations, timestamps, and rewards. Specifically, it contains 12 float32 action features (e.g., positions of left/right shoulder, elbow, wrist, and gripper), observation states (also 12 float32 features), top and side video observations (480x640 resolution, 3 channels, 30fps), timestamps, frame indices, task indices, etc. The dataset consists of 50 episodes, 20894 frames, divided into 2 tasks, with data files totaling 100MB and video files totaling 200MB.