This work proposes Dynamic Linear Epsilon-Greedy, a novel contextual multi-armed bandit algorithm that can adaptively assign personalized content to users while enabling unbiased statistical analysis. Traditional A/B testing and reinforcement learning approaches have trade-offs between empirical investigation and maximal impact on users. Our…

In an era of rapid technological growth in education, both teachers and students alike must adapt to up-to-date learning and teaching paradigms. Liveworksheets is advantageous in offering students a compilation of interactive sheets that provide instant online feedback. Nevertheless, whether utilizing Liveworksheets in self-study is efficient has…