Time to absorption in discounted reinforcement models

Stochastic Processes and their Applications

Volumn 109, Issue 1, 2004, Pages 1-12

  Pemantle, Robin ^a   Skyrms, Brian ^b  

^a OHIO STATE UNIVERSITY   (United States)

^b UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Exponential time; Friedman urn; Meta stable; Network; Potential well; Quasi stationary; Social network; Stochastic approximation; Three player game; Trap; Urn model

Indexed keywords

EID: 0242720147     PISSN: 03044149     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.spa.2003.08.003     Document Type: Article

References (29)

1. Anderlini L. Ianni A. Learning on a torus In: Bicchieri C. Jeffrey R. Skyrms B. (Eds.), The Dynamics of Norms 1997 87-107 Cambridge University Press Cambridge
2. Bannai E. Ito T. Algebraic Combinatorics I: Association Schemes 1984 Benjamin/Cummings Menlo Park, CA, USA
3. Barrat A. Weigt M. On the properties of small-world network models European Phys. J. B 13 2000 547
4. Benaïm M. A dynamical system approach to stochastic approximations SIAM J. Control Optim. 34 1996 437-472
5. Benaïm M. Hirsch M. Dynamics of Morse-Smale urn processes Ergodic Theory Dynamical Systems 15 1995 1005-1030
6. Benjamini I. Pemantle R. 2003 Probabilities for cooled Brownian motion to linger near the top of a hill, and application to a market share model. Preprint.
7. Bonacich P. Liggett T. 2002 Asymptotics of a matrix-valued Markov chain arising in sociology. Preprint.
8. Brouwer A. Cohen A. Neumaier A. Distance-Regular Graphs 1989 Springer Berlin
9. Bush R. Mosteller F. Stochastic Models for Learning 1955 Wiley New York
10. Davis B. Reinforced random walk Probab. Theory Related Fields 84 1990 203-229
11. Dembo A. Zeitouni O. Large Deviations Techniques and Applications 1993 Jones and Bartlett Boston
12. Eggenberger F. Pólya G. Uber die Statistik verketter vorgäge Zeit. Angew. Math. Mech. 1 1923 279-289
13. Ellison G. Learning, local interaction, and coordination Econometrica 61 1993 1047-1071
14. Flache A. Macy M. The weakness of strong ties: collective action failure in a highly cohesive group J. Math. Sociol. 21 1996 3-28
15. Freedman B. A simple urn model Comm. Pure Appl. Math. 2 1949 59-70
16. Freedman D. Bernard Friedman's urn Ann. Math. Statist. 36 1965 956-970
17. Fudenberg D. Kreps K. Learning mixed equilibria Games and Econom. Behav. 5 1993 320-367
18. Iosifescu M. Theodorescu R. Random Processes and Learning 1969 Springer New York
19. Lakshmivarahan S. Learning Algorithms: Theory and Applications 1981 Springer New York
20. Limic V. 2001 Attracting edge property for a class of reinforced random walks. Preprint. http://www.math.cornell.edu/~limic/.
21. Maynard Smith J. Evolution and the Theory of Games 1982 Cambridge University Press Cambridge
22. Norman M. Markov Processes and Learning Models 1972 Academic Press New York
23. Pemantle R. Nonconvergence to unstable points in urn models and stochastic approximations Ann. Probab. 18 1990 698-712
24. Pemantle R. Skyrms B. 2003a Network formation by reinforcement learning: the long and medium run. Preprint.
25. Pemantle R. Skyrms B. 2003b Reinforcement schemes may take a long time to exhibit limiting behavior. in preparation.
26. Robbins H. Monro S. A stochastic approximation method Ann. Math. Statist. 22 1951 400-407
27. Roth A. Erev I. Learning in extensive form games: experimental data and simple dynamic models in the intermediate term Games and Econom. Behav. 8 1995 164-212
28. Terwilliger P. 1996. Algebraic Combinatorics. Unpublished lecture notes.
29. Watts D. Strogatz S. Collective dynamics of "small-world" networks Nature 393 1998 440-442