Lecture

Reinforcement Learning: One-step Horizon (Bandit Problems)

In course

Sint cillum cillum aliqua ad culpa esse duis nulla elit eu culpa proident. Ullamco pariatur ea qui commodo duis duis velit sunt elit non pariatur. Dolore ex incididunt sint culpa qui officia laboris culpa. Incididunt sunt qui elit laboris voluptate sit esse in ut fugiat est quis aliqua occaecat.

Description

This lecture introduces the concept of Bandit Problems in Reinforcement Learning, where one has to choose between different actions and immediately receives a reward. The slides cover topics such as one-step horizon games, Q-values, optimal policy, iterative update rules, empirical averaging, and convergence in expectation.

Instructor

non enim

Aliquip qui mollit adipisicing esse culpa. Eiusmod cillum officia quis sit duis nisi. Ea aliqua culpa minim dolor amet ipsum veniam aliqua incididunt commodo id do aliqua ipsum. Exercitation anim tempor voluptate consectetur amet veniam aliqua adipisicing aliqua anim eiusmod. Eu adipisicing ea eiusmod enim cillum labore voluptate amet aliquip non nostrud. Id quis eu magna ut excepteur officia proident Lorem amet eu cupidatat occaecat. Proident anim aliqua labore ex amet qui excepteur anim aliquip.

Official source

https://mediaspace.epfl.ch/media/0_1zyrv1ci

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (36)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.