Three Body Problems in Evolutionary Game Dynamics: Convergence, Periodicity and Limit Cycles

We study the asymptotic behavior of replicator dynamics in settings of network interaction. We focus on three agent graphical games where each edge/game is either a 2x2 zero-sum or a 2x2 coordination game. Using tools from dynamical systems such as Lyapunov functions and invariant functions we establish that this simple family of games can exhibit an interesting range of behaviors such as global convergence, periodicity for all initial conditions as well as limit cycles. In contrast, we do not observe more complex behavior such as toroids or chaos while it is possible to reproduce them in slightly more complicated settings.

[1]  N. P. Bhatia,et al.  Dynamical Systems: Stability, Theory and Applications , 1967 .

[2]  Robert D. Kleinberg,et al.  Continuous-time model of structural balance , 2010, Proceedings of the National Academy of Sciences.

[3]  John S. Baras,et al.  The Evolution of Beliefs over Signed Social Networks , 2013, Oper. Res..

[4]  Georgios Piliouras,et al.  Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos , 2017, NIPS.

[5]  James D. Meiss,et al.  Differential dynamical systems , 2007, Mathematical modeling and computation.

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

[7]  Eizo Akiyama,et al.  Chaos in learning a simple two-person game , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[8]  T. Sideris.  Ordinary Differential Equations and Dynamical Systems , 2013 .

[9]  Jeff S. Shamma,et al.  Optimization Despite Chaos: Convex Relaxations to Complex Limit Sets via Poincaré Recurrence , 2014, SODA.

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

[11]  Peter Stone,et al.  Multiagent learning is not the answer. It is the question , 2007, Artif. Intell..

[12]  Michael P. Wellman,et al.  Foundations of multi-agent learning: Introduction to the special issue , 2007, Artif. Intell..

[13]  Henrik I. Christensen,et al.  Persistent patterns: multi-agent learning beyond equilibrium and utility , 2014, AAMAS.

[14]  Sanjeev Arora,et al.  The Multiplicative Weights Update Method: a Meta-Algorithm and Applications , 2012, Theory Comput..

[15]  Hujun Yin,et al.  Self-Organization, Emergence and Multi-Agent Systems , 2005, 2005 International Conference on Neural Networks and Brain.

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

[17]  Yoav Shoham,et al.  If multi-agent learning is the answer, what is the question? , 2007, Artif. Intell..

[18]  E. Akin,et al.  Cevolutionary instability of mixed Nash solutions , 1983, Journal of mathematical biology.

[19]  L. Barreira.  Poincaré recurrence:. old and new , 2006 .

[20]  Christos H. Papadimitriou,et al.  From Nash Equilibria to Chain Recurrent Sets: Solution Concepts and Topology , 2016, ITCS.

[21]  Christos H. Papadimitriou,et al.  Cycles in adversarial regularized learning , 2017, SODA.

[22]  E. Akin,et al.  Dynamics of games and genes: Discrete versus continuous time , 1983 .

[23]  BRIAN SKYRMS,et al.  Chaos in game dynamics , 1992, J. Log. Lang. Inf..

[24]  J. Hofbauer.  Evolutionary dynamics for bimatrix games: A Hamiltonian system? , 1996, Journal of mathematical biology.

[25]  Éva Tardos,et al.  Multiplicative updates outperform generic no-regret learning in congestion games: extended abstract , 2009, STOC '09.

[26]  I. Bendixson.  Sur les courbes définies par des équations différentielles , 1901 .

[27]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[28]  Vijay V. Vazirani,et al.  Rock-Paper-Scissors, Differential Games and Biological Diversity , 2017, ArXiv.

[29]  D. M. V. Hesteren.  Evolutionary Game Theory , 2017 .

[30]  Georgios Piliouras,et al.  Average Case Performance of Replicator Dynamics in Potential Games via Computing Regions of Attraction , 2014, EC.

[31]  Tsuyoshi Chawanya,et al.  Infinitely Many Attractors in Game Dynamics System , 1996 .

[32]  Leonard J. Schulman,et al.  Learning Dynamics and the Co-Evolution of Competing Sexual Species , 2017, ITCS.