Satisficing in Multi-Armed Bandit Problems

Paul Reverdy, Vaibhav Srivastava, Naomi Ehrich Leonard

Research output: Contribution to journalArticle

5 Scopus citations

Abstract

Satisficing is a relaxation of maximizing and allows for less risky decision making in the face of uncertainty. We propose two sets of satisficing objectives for the multi-armed bandit problem, where the objective is to achieve reward-based decision-making performance above a given threshold. We show that these new problems are equivalent to various standard multi-armed bandit problems with maximizing objectives and use the equivalence to find bounds on performance. The different objectives can result in qualitatively different behavior; for example, agents explore their options continually in one case and only a finite number of times in another. For the case of Gaussian rewards we show an additional equivalence between the two sets of satisficing objectives that allows algorithms developed for one set to be applied to the other. We then develop variants of the Upper Credible Limit (UCL) algorithm that solve the problems with satisficing objectives and show that these modified UCL algorithms achieve efficient satisficing performance.

Original languageEnglish (US)
Article number7795183
Pages (from-to)3788-3803
Number of pages16
JournalIEEE Transactions on Automatic Control
Volume62
Issue number8
DOIs
StatePublished - Aug 2017

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Keywords

  • Multi-armed bandit
  • upper credible limit (UCL)

Fingerprint Dive into the research topics of 'Satisficing in Multi-Armed Bandit Problems'. Together they form a unique fingerprint.

  • Cite this