Aasdfip/po2_train_2_branches_habitat_reward_gamm_0_9

该数据集包含了多个特征，如步骤编号、epsilon值、目标、上一次选择、当前选择、映射概率、图像路径、智能体位置、智能体朝向、里程表、距离目标、目标位置、任务完成情况、拒绝内容及其角色、前沿位置及其ID、距离目标的时间、到达目标的角度、选择的内容及其角色、目标回报、启发式参数、子回报以及分支回报等。数据集分为训练集，其中包含约18435个示例，总大小约为1.4GB。

The dataset includes multiple features such as step number, epsilon value, target, last choice, current choice, mapping probability, image path, agent position, agent heading, odometer, distance to goal, goal position, task completion status, rejected content and its role, frontier positions and their IDs, time to goal, angle to goal, chosen content and its role, target return, heuristic parameters, child returns, and branch returns. The dataset is split into a training set, which contains approximately 18,435 examples and has a total size of about 1.4GB.