A Language for Opponent Modeling in Repeated Games

Yakov Gal, Avi Pfeffer

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

Abstract / Description of output

Traditional game-theoretic formalisms, commonly used in multi-agent systems, invoke the assumption of common knowledge of rationality to justify a Nash equilibrium solution. It is assumed that all agents know a correct model of the game and are completely rational, and that this is common knowledge. However, real-life agents are partially irrational, they may use models other than the real world to make decisions, and they may be uncertain about their opponents’ decision making processes. For modeling boundedly-rational agents, a descriptive approach to game theory is needed, in which agents model their opponents and attempt to predict their behavior using their model. We present Networks of Influence Diagrams (NIDs), a language for descriptive decision and game theory that is based on graphical models. This paper describes NIDs and their syntax, and provides algorithms for solving NIDs and learning NID parameters. We also show that NIDs provide an elegant framework for opponent modeling that is more expressive than current approaches, leads to a better outcome than the Nash equilibrium strategy and is able to capture non-stationary distributions of opponents.
Original languageEnglish
Title of host publicationWorkshop on Game Theory and Decision Theory, AAMAS 2003
Number of pages8
Publication statusPublished - 2003
EventSecond international joint conference on Autonomous agents and multiagent systems - Melbourne, Australia
Duration: 14 Jul 200318 Jul 2003


ConferenceSecond international joint conference on Autonomous agents and multiagent systems
Abbreviated titleAAMAS '03


Dive into the research topics of 'A Language for Opponent Modeling in Repeated Games'. Together they form a unique fingerprint.

Cite this