Intrinsic noise in game dynamical learning.

Demographic noise has profound effects on evolutionary and population dynamics, as well as on chemical reaction systems and models of epidemiology. Such noise is intrinsic and due to the discreteness of the dynamics in finite populations. We here show that similar noise-sustained trajectories arise in game dynamical learning, where the stochasticity has a different origin: agents sample a finite number of moves of their opponents in between adaptation events. The limit of infinite batches results in deterministic modified replicator equations, whereas finite sampling leads to a stochastic dynamics. The characteristics of these fluctuations can be computed analytically using methods from statistical physics, and such noise can affect the attractors significantly, leading to noise-sustained cycling or removing periodic orbits of the standard replicator dynamics.

[1]  David Saad,et al.  On-Line Learning in Neural Networks , 1999 .

[2]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[3]  H G Solari,et al.  Population dynamics: Poisson approximation and its relation to the Langevin process. , 2001, Physical review letters.

[4]  A J McKane,et al.  Predator-prey cycles from resonant amplification of demographic stochasticity. , 2005, Physical review letters.

[5]  D. Fudenberg,et al.  Evolutionary cycles of cooperation and defection. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[6]  A. McKane,et al.  Amplified Biochemical Oscillations in Cellular Systems , 2006, q-bio/0604001.

[7]  Philip A. Gale,et al.  Cytosine substituted calix[4]pyrroles: Neutral receptors for 5′-guanosine monophosphate , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Fernando Vega-Redondo,et al.  Economics and the theory of games: Contents , 2003 .

[9]  J M Smith,et al.  Evolution and the theory of games , 1976 .

[10]  Colin Camerer,et al.  Foundations of Human Sociality - Economic Experiments and Ethnographic: Evidence From Fifteen Small-Scale Societies , 2004 .

[11]  W. Ebeling.  Stochastic Processes in Physics and Chemistry , 1995 .

[12]  M. Pascual,et al.  Stochastic amplification in epidemics , 2007, Journal of The Royal Society Interface.

[13]  L. Imhof,et al.  Stochasticity and evolutionary stability. , 2006, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  Elsayed Ahmed,et al.  SATO–CRUTCHFIELD FORMULATION FOR SOME EVOLUTIONARY GAMES , 2003 .

[15]  E. Rowland.  Theory of Games and Economic Behavior , 1946, Nature.

[16]  J. M. Smith,et al.  The Logic of Animal Conflict , 1973, Nature.

[17]  C. Hauert,et al.  Coevolutionary dynamics: from finite to infinite populations. , 2004, Physical review letters.

[18]  M. M. Telo da Gama,et al.  Stochastic fluctuations in epidemics on networks , 2007, Journal of The Royal Society Interface.

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

[20]  Teck-Hua Ho,et al.  Self-tuning experience weighted attraction learning in games , 2007, J. Econ. Theory.

[21]  N. Kampen,et al.  Stochastic processes in physics and chemistry , 1981 .

[22]  Erwin Frey,et al.  Anomalous finite-size effects in the Battle of the Sexes , 2007, 0709.0225.

[23]  J. Crutchfield,et al.  Coupled replicator equations for the dynamics of learning in multiagent systems. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[24]  Arne Traulsen,et al.  Cyclic dominance and biodiversity in well-mixed populations. , 2008, Physical review letters.

[25]  M. Bacharach.  Economics and the Theory of Games , 2019 .