Fast adaptive learning in repeated stochastic games by game abstraction

Mohamed Elidrisi, Nicholas Johnson, Maria Gini, Jacob Crandall

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Scopus citations

Abstract

An agent must learn and adapt quickly when playing against other agents. This process is challenging in particular when playing in stochastic environments against other learning agents. In this paper, we introduce a fast and adaptive learning algorithm for repeated stochastic games (FAL-SG). FAL-SG utilizes lossy game abstraction to reduce the state space of the game and facilitate learning and adapting rapidly. We analyze FAL-SG's performance by proving bounds on the abstraction loss and prediction mistakes and show that FAL-SG satisfies three criteria prescribed for multiagent learning algorithms. We successfully establish the robustness and scalability of FAL-SG with extensive theoretical and experimental results.

Original languageEnglish (US)
Title of host publication13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages1141-1148
Number of pages8
ISBN (Electronic)9781634391313
StatePublished - Jan 1 2014
Event13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 - Paris, France
Duration: May 5 2014May 9 2014

Publication series

Name13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
Volume2

Other

Other13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
CountryFrance
CityParis
Period5/5/145/9/14

Keywords

  • Adversarial learning
  • Game theory
  • Multiagent learning

Fingerprint Dive into the research topics of 'Fast adaptive learning in repeated stochastic games by game abstraction'. Together they form a unique fingerprint.

Cite this