Data and code underlying the master thesis: Using Reinforcement Learning to Personalize Daily Step Goals for a Collaborative Dialogue with a Virtual Coach

This dataset contains the data and analysis code from the observational study conducted for the thesis: Using Reinforcement Learning to Personalize Daily Step Goals for a Collaborative Dialogue with a Virtual Coach. In this thesis, we studied the use of reinforcement learning to personalize daily step goal proposals based on people's personal factors, such as mood and self-motivation. To train the reinforcement learning model, we ran an observational study with a virtual coach to gather data on people's personal factors. We then ran analyses on simulations using the collected data to investigate the effectiveness of the model.

本数据集收录了某学位论文对应的观察性研究的全部数据与分析代码，该论文题为《利用强化学习实现虚拟教练协作对话场景下的个性化每日步数目标（Using Reinforcement Learning to Personalize Daily Step Goals for a Collaborative Dialogue with a Virtual Coach）。本研究探索了基于情绪、自我动机等个人因素，运用强化学习生成个性化每日步数目标推荐方案的方法。为训练强化学习模型，我们开展了一项搭载虚拟教练的观察性研究，以收集用户个人因素相关数据。随后，我们基于所收集的数据开展仿真分析，以探究该模型的有效性。