Home > Research > Publications & Outputs > Robustness Properties in Fictitious-Play-Type A...

Associated organisational unit

Electronic data

  • 1609.08830

    Submitted manuscript, 334 KB, PDF document

  • M109322Accepted

    Accepted author manuscript, 331 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Robustness Properties in Fictitious-Play-Type Algorithms

Research output: Contribution to journalJournal article

Published
Close
<mark>Journal publication date</mark>24/10/2017
<mark>Journal</mark>SIAM Journal on Control and Optimization
Volume55
Number of pages24
Pages (from-to)3295-3318
Publication statusPublished
Original languageEnglish

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 action given their forecast. We provide a unifed 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 game-theoretic 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.