Escort Evolutionary Game Theory

Abstract A family of replicator-like dynamics, called the escort replicator dynamic, is constructed using information-geometric concepts and generalized information divergences from information geometry and statistical thermodynamics. A single-formula Lyapunov function is given that covers the entire class of dynamics, which includes the replicator dynamic and the projection dynamic, as well as several new dynamics. A further class is discussed that allows for more variation, such as variable intensities of selection.

[1]  N. Čencov.  Statistical Decision Rules and Optimal Inference , 2000 .

[2]  Dominik Endres,et al.  A new metric for probability distributions , 2003, IEEE Transactions on Information Theory.

[3]  Stefan Thurner,et al.  Unified model for network dynamics exhibiting nonextensive statistics. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[4]  M. Nowak,et al.  Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm , 2022 .

[5]  William H. Sandholm,et al.  The projection dynamic and the replicator dynamic , 2008, Games Econ. Behav..

[6]  S. Frank.  Natural selection maximizes Fisher information , 2009, Journal of evolutionary biology.

[7]  Shun-ichi Amari,et al.  Methods of information geometry , 2000 .

[8]  Alexandre Souto Martinez,et al.  Continuous growth models in terms of generalized logarithm and exponential functions , 2008, 0803.2635.

[9]  Shalabh Bhatnagar,et al.  Properties of Kullback-Leibler cross-entropy minimization in nonextensive framework , 2005, Proceedings. International Symposium on Information Theory, 2005. ISIT 2005..

[10]  William H. Sandholm,et al.  Population Games And Evolutionary Dynamics , 2010, Economic learning and social evolution.

[11]  Ryota Horie.  An optimization framework of biological dynamical systems. , 2008, Journal of theoretical biology.

[12]  A. Martinez,et al.  Generalized exponential function and discrete growth models , 2008, 0803.3089.

[13]  Igor Vajda,et al.  On asymptotic properties of information-theoretic divergences , 2003, IEEE Transactions on Information Theory.

[14]  Marc Harper,et al.  Information Geometry and Evolutionary Game Theory , 2009, ArXiv.

[15]  C. Tsallis,et al.  Information gain within nonextensive thermostatistics , 1998 .

[16]  C. Shalizi.  Dynamics of Bayesian Updating with Dependent Data and Misspecified Models , 2009, 0901.1342.

[17]  J. Naudts.  Estimators, escort probabilities, and phi-exponential families in statistical physics , 2004, math-ph/0402005.

[18]  J. Naudts.  Deformed exponentials and logarithms in generalized thermostatistics , 2002, cond-mat/0203489.

[19]  A. Ohara.  Geometry of distributions associated with Tsallis statistics and properties of relative entropy minimization , 2007 .

[20]  N. Ay,et al.  On a Notion of Linear Replicator Equations , 2005 .

[21]  Rajiv Sethi.  Strategy-Specific Barriers to Learning and Nonmonotonic Selection Dynamics☆☆☆ , 1998 .

[22]  James P. Crutchfield,et al.  Stability and diversity in collective adaptation , 2004, nlin/0408039.

[23]  S. Furuichi.  On the maximum entropy principle and the minimization of the Fisher information in Tsallis statistics , 2009, 1001.1383.

[24]  S. Shahshahani,et al.  A New Mathematical Framework for the Study of Linkage and Selection , 1979 .

[25]  E. Akin.  The Differential Geometry of Population Genetics and Evolutionary Games , 1990 .

[26]  Sumiyoshi Abe.  Geometry of escort distributions. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[27]  C. Tsallis.  Possible generalization of Boltzmann-Gibbs statistics , 1988 .

[28]  Reinoud A.M.G. Joosten,et al.  Generalized projection dynamics in evolutionary game theory , 2008 .

[29]  Jan Naudts,et al.  Generalised Exponential Families and Associated Entropy Functions , 2008, Entropy.

[30]  Flemming Topsøe,et al.  Some inequalities for information divergence and related measures of discrimination , 2000, IEEE Trans. Inf. Theory.

[31]  Jianhua Lin,et al.  Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[32]  S. Amari,et al.  Gradient systems in view of information geometry , 1995 .

[33]  Christopher J. Lee.  Empirical Information Metrics for Prediction Power and Experiment Planning , 2011, Inf..

[34]  N. N. Chent︠s︡ov.  Statistical decision rules and optimal inference , 1982 .

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

[36]  M. Narasimha Murty,et al.  Generalized Evolutionary Algorithm based on Tsallis Statistics , 2004, ArXiv.

[37]  Jörgen W. Weibull,et al.  Evolutionary Game Theory , 1996 .

[38]  M. Narasimha Murty,et al.  Information theoretic justification of Boltzmann selection and its generalization to Tsallis case , 2005, 2005 IEEE Congress on Evolutionary Computation.