Graphical Models for Bandit Problems release_l5vdorprcvdo3c3sagx4yftsaq

by Kareem Amin, Michael Kearns, Umar Syed

Released as a report .

2012  

Abstract

We introduce a rich class of graphical models for multi-armed bandit problems that permit both the state or context space and the action space to be very large, yet succinctly specify the payoffs for any context-action pair. Our main result is an algorithm for such models whose regret is bounded by the number of parameters and whose running time depends only on the treewidth of the graph substructure induced by the action space.
In text/plain format

Archived Files and Locations

application/pdf  213.8 kB
file_rp2svbel7jenrm4en67ejqoeim
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  report
Stage   submitted
Date   2012-02-14
Version   v1
Language   en ?
Number  UAI-P-2011-PG-1-10
arXiv  1202.3782v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: bbde71dc-9a3e-4557-98bb-ca77145e8b1c
API URL: JSON