Robustness properties in fictitious-play-type algorithms

Brian Swenson, Soummya Kar, João Xavier, David S. Leslie

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

Fictitious play (FP) is a canonical game-theoretic learning algorithm which has been deployed extensively in decentralized control scenarios. However standard treatments of FP, and of many other game-theoretic models, assume rather idealistic conditions which rarely hold in realistic control scenarios. This paper considers a broad class of best response learning algorithms that we refer to as FP-type algorithms. In such an algorithm, given some (possibly limited) information about the history of actions, each individual forecasts the future play and chooses a (myopic) best response strategy given their forecast. We provide a unified analysis of the behavior of FP-type algorithms under an important class of perturbations, thus demonstrating robustness to deviations from the idealistic operating conditions that have been previously assumed. This robustness result is then used to derive convergence results for two control-relevant relaxations of standard gametheoretic applications: distributed (network-based) implementation without full observability and asynchronous deployment (including in continuous time). In each case the results follow as a direct consequence of the main robustness result.

Original languageEnglish (US)
Pages (from-to)3295-3318
Number of pages24
JournalSIAM Journal on Control and Optimization
Volume55
Issue number5
DOIs
StatePublished - 2017

All Science Journal Classification (ASJC) codes

  • Control and Optimization
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Robustness properties in fictitious-play-type algorithms'. Together they form a unique fingerprint.

Cite this