Probe and Adjust in Information Transfer Games

We study a low-rationality learning dynamics called probe and adjust. Our emphasis is on its properties in games of information transfer such as the Lewis signaling game or the Bala-Goyal network game. These games fall into the class of weakly better reply games, in which, starting from any action profile, there is a weakly better reply path to a strict Nash equilibrium. We prove that probe and adjust will be close to strict Nash equilibria in this class of games with arbitrarily high probability. In addition, we compare these asymptotic properties to short-run behavior.

[1]  Brian Skyrms,et al.  Emergence of a Signaling Network with Probe and Adjust , 2013 .

[2]  H. Peyton Young,et al.  Strategic Learning and Its Limits , 2004 .

[3]  H. Peyton Young,et al.  Learning by trial and error , 2009, Games Econ. Behav..

[4]  Alan W. Beggs,et al.  On the convergence of reinforcement learning , 2005, J. Econ. Theory.

[5]  Christina Pawlowitsch,et al.  Why evolution does not always lead to an optimal signaling system , 2008, Games Econ. Behav..

[6]  Simon M. Huttegger.  Probe and Adjust , 2013 .

[7]  Brian Skyrms,et al.  Signals: Evolution, Learning, and Information , 2010 .

[8]  Jason R. Marden,et al.  Payoff-Based Dynamics for Multiplayer Weakly Acyclic Games , 2009, SIAM J. Control. Optim..

[9]  K. Wärneryd.  Cheap Talk, Coordination, and Evolutionary Stability , 1993 .

[10]  B. Skyrms.  Evolution of the social contract , 1996 .

[11]  Martin Posch,et al.  Attainability of boundary points under reinforcement learning , 2005, Games Econ. Behav..

[12]  Simon M. Huttegger.  Evolution and the Explanation of Meaning* , 2007, Philosophy of Science.

[13]  Steven O. Kimbrough,et al.  Learning to Collude Tacitly on Production Levels by Oligopolistic Agents , 2009 .

[14]  H. Peyton Young,et al.  Individual Strategy and Social Structure , 2020 .

[15]  E. Hopkins.  Two Competing Models of How People Learn in Games (first version) , 1999 .

[16]  H. Young,et al.  The Evolution of Conventions , 1993 .

[17]  Brian Skyrms,et al.  LEARNING TO SIGNAL WITH PROBE AND ADJUST , 2012, Episteme.

[18]  Jeffrey Barrett,et al.  The role of forgetting in the evolution and learning of language , 2009, J. Exp. Theor. Artif. Intell..

[19]  Stanislav Volkov,et al.  Learning to signal: Analysis of a micro-level reinforcement model , 2009 .

[20]  David Lewis.  Convention: A Philosophical Study , 1986 .

[21]  D. Fudenberg,et al.  The Theory of Learning in Games , 1998 .

[22]  L. Samuelson,et al.  Evolutionary stability in repeated games played by finite automata , 1992 .

[23]  Brian Skyrms,et al.  Emergence of Information Transfer by Inductive Learning , 2008, Stud Logica.

[24]  Brian Skyrms,et al.  Reinforcement learning in signaling game , 2011, 1103.5818.

[25]  Sanjeev Goyal,et al.  A Noncooperative Model of Network Formation , 2000 .