Asymptotically Optimal Algorithms for Budgeted Multiple Play Bandits release_p5j45bcqxrbgpjwafonvnq5pfq

by Alexander Luedtke , Antoine Chambaz

Released as a article .

2016  

Abstract

We study a generalization of the multi-armed bandit problem with multiple plays where there is a cost associated with pulling each arm and the agent has a budget at each time that dictates how much she can expect to spend. We derive an asymptotic regret lower bound for any uniformly efficient algorithm in our setting. We then study a variant of Thompson sampling for Bernoulli rewards and a variant of KL-UCB for both single-parameter exponential families and bounded, finitely supported rewards. We show these algorithms are asymptotically optimal, both in rate and leading problem-dependent constants, including in the thick margin setting where multiple arms fall on the decision boundary.
In text/plain format

Archived Files and Locations

application/pdf  851.5 kB
file_jjdkcax7zfdgleerqrs4ijntwm
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2016-06-30
Version   v1
Language   en ?
arXiv  1606.09388v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 0b618ce9-bafe-4dee-bcc5-8bf95a8f6f64
API URL: JSON