Video library: A. V. Nazin, Randomized strategies of a multi-armed bandit based on mirror descent method

Videolibrary

RUS ENG

JOURNALS PEOPLE ORGANISATIONS CONFERENCES SEMINARS VIDEO LIBRARY PACKAGE AMSBIB

JavaScript is disabled in your browser. Please switch it on to enable full functionality of the website

	Video Library
	Archive
	Most viewed videos

	Search
	RSS
	New in collection

Information Technologies and Systems 2013
September 5, 2013 14:30–15:30, Svetlogorsk (Kaliningrad Region, Russia)

Randomized strategies of a multi-armed bandit based on mirror descent method

A. V. Nazin

Institute of Control Sciences, Russian Academy of Sciences, Moscow

*Video records:*
	Flash Video	321.1 Mb
	MP4	420.2 Mb

Abstract: We consider the problem of a multi-armed bandit and present an optimization approach based on mirror descent. Lower and upper bounds for the difference between the mean and the minimal losses are given for a broad class of problems

Registration to the website

Logotypes