Bandit Problems with Arbitrary Side Observations

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

A bandit problem with side observations is an extension of the traditional two-armed bandit problem, in which the decision maker has access to side information before deciding which arm to pull. In this paper, the essential properties of the side observations that allow achievability results with respect to the minimal inferior sampling time are extracted and formulated. The sufficient conditions for good side information obtained here contain various kinds of random processes as special cases, including i.i.d sequences, Markov chains, periodic sequences, etc. A necessary condition is also provided, giving more insight into the nature of bandit problems with side observations. A game-theoretic approach simplifies the analysis and justifies the viewpoint that the side observation serves as an index of different sub-bandit machines.

Original languageEnglish (US)
Pages (from-to)2948-2953
Number of pages6
JournalProceedings of the IEEE Conference on Decision and Control
Volume3
StatePublished - Dec 1 2003
Event42nd IEEE Conference on Decision and Control - Maui, HI, United States
Duration: Dec 9 2003Dec 12 2003

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Bandit Problems with Arbitrary Side Observations'. Together they form a unique fingerprint.

Cite this