Extensive-form games with heterogeneous populations: solution concepts, equilibria characterization, learning dynamics

The adoption of Nash equilibrium (NE) in real-world settings is often impractical due to its too restrictive assumptions. Game theory and artificial intelligence provide alternative (relaxed) solution concepts. When knowledge about opponents' utilities and types are not available, the appropriate solution concept for extensive-form games is the self- confirming equilibrium (SCE), which relaxes NE allowing agents to have wrong beliefs off the equilibrium path. In this paper, we provide the first computational and learning study of the situations in which a two-agent extensive-form game is played by heterogeneous populations of individuals that repeatedly match (e.g., eBay): we extend the SCE concept, we study the equilibrium computation problem, and we study how these equilibria affect learning dynamics. We show that SCEs are crucial for characterizing both stable states of learning dynamics and the dynamics themselves.

[1]  Nicola Gatti,et al.  New results on the verification of Nash refinements for extensive-form games , 2012, AAMAS.

[2]  C. E. Lemke,et al.  Equilibrium Points of Bimatrix Games , 1964 .

[3]  D. Fudenberg,et al.  Self-confirming equilibrium , 1993 .

[4]  Vincent Conitzer,et al.  Mixed-Integer Programming Methods for Finding Nash Equilibria , 2005, AAAI.

[5]  Yoav Shoham,et al.  Multiagent Systems - Algorithmic, Game-Theoretic, and Logical Foundations , 2009 .

[6]  Paul W. Goldberg,et al.  The complexity of computing a Nash equilibrium , 2006, STOC '06.

[7]  Drew Fudenberg,et al.  Learning to Play Bayesian Games , 2001, Games Econ. Behav..

[8]  Tuomas Sandholm,et al.  Algorithms for Closed Under Rational Behavior (CURB) Sets , 2010, J. Artif. Intell. Res..

[9]  Nicola Gatti,et al.  Computing a self-confirming equilibrium in two-player extensive-form games , 2011, AAMAS.

[10]  Michael P. Wellman,et al.  Self-Confirming Price Prediction for Bidding in Simultaneous Ascending Auctions , 2005, UAI.

[11]  D. Avis,et al.  Enumeration of Nash equilibria for two-player games , 2010 .

[12]  Gerhard Weiss,et al.  Multiagent Systems , 1999 .

[13]  Yoav Shoham,et al.  Simple search methods for finding a Nash equilibrium , 2004, Games Econ. Behav..

[14]  D. Koller,et al.  Efficient Computation of Equilibria for Extensive Two-Person Games , 1996 .

[15]  C. E. Lemke.  Some pivot schemes for the linear complementarity problem , 1978 .

[16]  Peter Bro Miltersen,et al.  Computing sequential equilibria for two-player games , 2006, SODA '06.

[17]  Karl Tuyls,et al.  An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games , 2005, Autonomous Agents and Multi-Agent Systems.

[18]  Sjaak Hurkens.  Learning by Forgetful Players , 1995 .

[19]  R. Cressman.  Evolutionary Dynamics and Extensive Form Games , 2003 .

[20]  Simon Parsons,et al.  Using Evolutionary Game-Theory to Analyse the Performance of Trading Strategies in a Continuous Double Auction Market , 2007, Adaptive Agents and Multi-Agents Systems.