xqx-chloe1/po2_val_2_branches_with_q_predictions_mr2ckpt1800
收藏Hugging Face2025-10-22 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/xqx-chloe1/po2_val_2_branches_with_q_predictions_mr2ckpt1800
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是一个包含智能体在环境中导航和决策相关信息的集合，具体包括智能体的位置、朝向、所做选择、环境中的目标位置、到目标的距离等特征，以及与任务相关的回报值和提示信息。数据集分为训练集，适用于机器学习和强化学习相关的研究和开发。
This dataset is a collection of information related to an agents navigation and decision-making in an environment, including features such as the agents position, orientation, choices made, target positions in the environment, distance to the target, and associated reward values and prompt information. The dataset is split into a training set, suitable for machine learning and reinforcement learning research and development.
提供机构：
xqx-chloe1
