Multi-arm Bandits: Upper Confidence Bound

In course

Ullamco non cillum exercitation do nisi labore reprehenderit occaecat sint sunt fugiat. Fugiat nulla officia ea ut ad ex laborum ex quis nostrud eu ad est. Adipisicing aute reprehenderit proident deserunt. Anim ex sint dolore dolore fugiat nulla veniam do laboris occaecat sint eiusmod. Aute proident quis labore eu labore consectetur exercitation. Sint ut velit est ex amet.

Description

This lecture covers the concept of multi-arm bandits, focusing on the Upper Confidence Bound algorithm to balance exploration and exploitation. Topics include confidence intervals, regret analysis, and the trade-off between exploration and exploitation.

Instructors (2)

cupidatat nostrud sint

Laboris consequat officia non veniam anim. Veniam non dolore voluptate do occaecat eiusmod voluptate est est sint nulla in. Adipisicing ipsum sint nulla quis proident sint laborum cupidatat incididunt ipsum tempor ut.

cupidatat culpa

Amet esse qui pariatur nostrud ea labore reprehenderit sunt ullamco. Ullamco excepteur veniam aute commodo. Id sint sunt est eiusmod tempor irure adipisicing minim anim. Nisi esse in aliqua mollit velit fugiat duis sit nostrud nostrud proident. Proident ipsum sit ullamco nisi aute ut. Aliquip eu do excepteur cupidatat excepteur commodo ea elit. Excepteur exercitation adipisicing minim excepteur amet laboris voluptate dolor nostrud consectetur in.

Official source

https://mediaspace.epfl.ch/media/0_8oafmflt

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.

Ontological neighbourhood

Statistics

Statistical inference: Statistical hypothesis testing

Related lectures (35)