Emergence of Information Transfer by Inductive Learning

We study a simple game theoretic model of information transfer which we consider to be a baseline model for capturing strategic aspects of epistemological questions. In particular, we focus on the question whether simple learning rules lead to an efficient transfer of information. We find that reinforcement learning, which is based exclusively on payoff experiences, is inadequate to generate efficient networks of information transfer. Fictitious play, the game theoretic counterpart to Carnapian inductive logic and a more sophisticated kind of learning, suffices to produce efficiency in information transfer.

[1]  A. Goldman.  Knowledge in a Social World , 1999 .

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

[3]  Jean-François Laslier,et al.  A Behavioral Learning Process in Games , 2001, Games Econ. Behav..

[4]  M. Benaïm.  Dynamics of stochastic approximation algorithms , 1999 .

[5]  A. Roth,et al.  Learning in Extensive-Form Games: Experimental Data and Simple Dynamic Models in the Intermediate Term* , 1995 .

[6]  Ben van der Genugten,et al.  A Weakened Form of Fictitious Play in Two-Person Zero-Sum Games , 2000, IGTR.

[7]  K. Sigmund,et al.  The efficiency of adapting aspiration levels , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

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

[9]  Rudolf Carnap,et al.  The continuum of inductive methods , 1952 .

[10]  A. Roth,et al.  Predicting How People Play Games: Reinforcement Learning in Experimental Games with Unique, Mixed Strategy Equilibria , 1998 .

[11]  Rudolf Carnap,et al.  Logical foundations of probability , 1951 .

[12]  B. Malinowski.  Argonauts of the Western Pacific: An Account of Native Enterprise and Adventure in the Archipelagoes of Melanesian New Guinea , 2002 .

[13]  Philip Kitcher,et al.  The Division of Cognitive Labor , 1990 .

[14]  Sandy L. Zabell,et al.  Symmetry and its discontents , 2005 .

[15]  R. Durrett.  Probability: Theory and Examples , 1993 .

[16]  David Lindley,et al.  Logical foundations of probability , 1951 .

[17]  B Skyrms,et al.  A dynamic model of social network formation. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Rita S. Kipp,et al.  From a Shattered Sun: Hierarchy, Gender, and Alliance in the Tanimbar Islands , 1994 .

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

[20]  Brian Skyrms.  Carnapian inductive logic for Markov chains , 1991 .

[21]  Kevin J. S. Zollman.  The Epistemic Benefit of Transient Diversity , 2009 .

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

[23]  Josef Hofbauer,et al.  Evolutionary Games and Population Dynamics , 1998 .

[24]  B. D. Finetti,et al.  Foresight: Its Logical Laws, Its Subjective Sources , 1992 .

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

[26]  B. Malinowski.  Argonauts of the Western Pacific , 1922 .

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

[28]  E. J. Collins,et al.  Convergent multiple-timescales reinforcement learning algorithms in normal form games , 2003 .

[29]  Stanislav Volkov,et al.  Vertex-reinforced random walk on Z has finite range , 1999 .

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

[31]  A. Rustichini.  Optimal Properties of Stimulus-Response Learning Models* , 1999 .

[32]  D. Monderer,et al.  A 2£ 2 Game without the Fictitious Play Property ⁄ , 1996 .

[33]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[34]  David S. Leslie,et al.  Generalised weakened fictitious play , 2006, Games Econ. Behav..

[35]  Colin Camerer,et al.  Experience‐weighted Attraction Learning in Normal Form Games , 1999 .