Convergence of reinforcement learning to Nash equilibrium: A search-market experiment

Physica A: Statistical Mechanics and its Applications

Volumn 355, Issue 1, 2005, Pages 119-130

  Darmon, Eric ^a   Waldeck, Roger ^b  

^a GREDEG CNRS   (France)

^b ECOLE DES MINES DE NANTES   (France)

Author keywords

Agent based modeling; Nash equilibrium; Reinforcement learning; Search market

Indexed keywords

COMPUTER SIMULATION; DISPERSIONS; ELECTRONIC COMMERCE; GAME THEORY; LEARNING ALGORITHMS; MARKETING; MATHEMATICAL MODELS;

AGENT-BASED MODELING; NASH EQUILIBRIUM; REINFORCEMENT LEARNING; SEARCH MARKET;

LEARNING SYSTEMS;

EID: 21444454057     PISSN: 03784371     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.physa.2005.02.074     Document Type: Conference Paper

References (10)

1. I. Erev, and A.E. Roth Predicting how people play games: reinforcement learning in experimental games with unique, mixed strategy equilibria Am. Economic Rev. 88 1998 848 881
2. A.M. Bell, Reinforcement learning rules in a repeated game, Computat. Econ. (2001) 89-111.
3. A.P. Kirman, and N.J. Vriend Evolving market structure: an ACE model of price dispersion and loyalty J. Econ. Dynam. Control 25 2001 459 502
4. T. Brenner A behavioural learning approach to the dynamics of prices Computat. Econ. 19 2002 67 94
5. E. Brynjolfsson, and M. Smith Frictionless commerce? A comparison of internet and conventional retailers Manage. Sci. 46 2000 563 585
6. M.D. Smith, J. Bailey, and E. Brynjolfsson Understanding digital markets: review and assessment E. Brinjolffson B. Kahin Understanding the Digital Economy: Data, Tools and Research 2000 MIT Press Cambridge, MA
7. R. Waldeck, Search and price competition, J. Econ. Behav. Organ., forthcoming.
8. E. Darmon, R. Waldeck, Technical appendix of "Convergence of reinforcement learning to Nash equilibrium: a search-market experiment", document available at http://e.darmon.free.fr/in/fssmarket/techphysa.pdf (2005).
9. E. Darmon, R. Waldeck, Does it matter to play Nash? The case of adaptive sellers, Working Paper downloadable at http://e.darmon.free.fr/in/fssmarket/ paperfss.pdf (2004).
10. M. Posch Cycling in a stochastic learning algorithm for normal form games J. Evol. Econ. 7 1997 193 207