Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers risk minimization from adaptively collected data with guarantees for policy learning, focusing on adaptive experiments, sequential observations, and the importance of exploration strategies. The instructor discusses the key concepts, such as E-greedy exploration, martingale difference sequence, and the theoretical foundations behind policy learning.