Data-driven entropic spatially inhomogeneous evolutionary games

We introduce novel multi-agent interaction models of entropic spatially inhomogeneous evolutionary undisclosed games and their quasi-static limits. These evolutions vastly generalize first and second order dynamics. Besides the well-posedness of these novel forms of multi-agent interactions, we are concerned with the learnability of individual payoff functions from observation data. We formulate the payoff learning as a variational problem, minimizing the discrepancy between the observations and the predictions by the payoff function. The inferred payoff function can then be used to simulate further evolutions, which are fully data-driven. We prove convergence of minimizing solutions obtained from a finite number of observations to a mean field limit and the minimal value provides a quantitative error bound on the data-driven evolutions. The abstract framework is fully constructive and numerically implementable. We illustrate this on computational examples where a ground truth payoff function is known and on examples where this is not the case, including a model for pedestrian movement.

[1]  Vicsek,et al.  Novel type of phase transition in a system of self-driven particles. , 1995, Physical review letters.

[2]  M. Fornasier,et al.  Inferring Interaction Rules From Observations of Evolutive Systems I: The Variational Approach , 2016, 1602.00342.

[3]  Marco Morandotti,et al.  An alternate Lagrangian scheme for spatially inhomogeneous evolutionary games. , 2020, 2005.07479.

[4]  Trenton Kirchdoerfer,et al.  Data-driven computational mechanics , 2015, 1510.04232.

[5]  Ken Sugawara,et al.  Cooperative acceleration of task performance: foraging behavior of interacting multi-robots system , 1997 .

[6]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[7]  J. Urry.  Complexity , 2006, Interpreting Art.

[8]  Giovanni Scilla,et al.  Delayed loss of stability in singularly perturbed finite-dimensional gradient flows , 2018, Asymptot. Anal..

[9]  Hayden Schaeffer,et al.  Extracting Sparse High-Dimensional Dynamics from Limited Data , 2017, SIAM J. Appl. Math..

[10]  Massimo Fornasier,et al.  Particle, kinetic, and hydrodynamic models of swarming , 2010 .

[11]  Andrea L. Bertozzi,et al.  Multi-Vehicle Flocking: Scalability of Cooperative Control Algorithms using Pairwise Potentials , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[12]  H. Engl,et al.  Tikhonov regularization applied to the inverse problem of option pricing: convergence analysis and rates , 2005 .

[13]  U. Krause.  A DISCRETE NONLINEAR AND NON–AUTONOMOUS MODEL OF CONSENSUS FORMATION , 2007 .

[14]  Tu,et al.  Long-Range Order in a Two-Dimensional Dynamical XY Model: How Birds Fly Together. , 1995, Physical review letters.

[15]  J. Carrillo,et al.  Double milling in self-propelled swarms from kinetic theory , 2009 .

[16]  J. A. Carrillo,et al.  The derivation of swarming models: Mean-field limit and Wasserstein distances , 2013, 1304.5776.

[17]  Christian A. Yates,et al.  Inherent noise can facilitate coherence in collective swarm motion , 2009, Proceedings of the National Academy of Sciences.

[18]  Jos'e A. Carrillo,et al.  A well-posedness theory in measures for some kinetic models of collective motion , 2009, 0907.3901.

[19]  G. Parisi,et al.  Interaction ruling animal collective behavior depends on topological rather than metric distance: Evidence from a field study , 2007, Proceedings of the National Academy of Sciences.

[20]  S. Conti,et al.  Data-Driven Problems in Elasticity , 2017, 1708.02880.

[21]  Multiscale analysis of singularly perturbed finite dimensional gradient flows: the minimizing movement approach , 2017, Nonlinearity.

[22]  Peter E. Caines,et al.  Synthesis of Cucker-Smale type flocking via Mean Field stochastic control theory: Nash equilibria , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[23]  James W. Minett,et al.  Self-organization and selection in the emergence of vocabulary , 2002, Complex..

[24]  P. Caines,et al.  Nash Equilibria for Large-Population Linear Stochastic Systems of Weakly Coupled Agents , 2005 .

[25]  Stéphane Crépey,et al.  Calibration of the Local Volatility in a Generalized Black-Scholes Model Using Tikhonov Regularization , 2003, SIAM J. Math. Anal..

[26]  I D Couzin,et al.  Self-organized lane formation and optimized traffic flow in army ants , 2003, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[27]  L. Segel,et al.  Initiation of slime mold aggregation viewed as an instability. , 1970, Journal of theoretical biology.

[28]  J. Eisert,et al.  Extracting dynamical equations from experimental data is NP hard. , 2010, Physical review letters.

[29]  U. Ascher,et al.  Data driven recovery of local volatility surfaces , 2015, 1512.07660.

[30]  M. Fornasier,et al.  Spatially Inhomogeneous Evolutionary Games , 2018, Communications on Pure and Applied Mathematics.

[31]  H. Chaté,et al.  Onset of collective and cohesive motion. , 2004, Physical review letters.

[32]  P. Lions,et al.  Mean field games , 2007 .

[33]  R. Rosenthal,et al.  Anonymous sequential games , 1988 .

[34]  Marco Morandotti,et al.  Mean-field Analysis of Multipopulation Dynamics with Label Switching , 2019, SIAM J. Math. Anal..

[35]  Mauro Garavello,et al.  Traffic flow on networks : conservation laws models , 2006 .

[36]  Hiro-Sato Niwa.  Self-organizing Dynamic Model of Fish Schooling , 1994 .

[37]  I. Couzin,et al.  Effective leadership and decision-making in animal groups on the move , 2005, Nature.

[38]  Hayden Schaeffer,et al.  Learning Dynamical Systems and Bifurcation via Group Sparsity , 2017, 1709.01558.

[39]  Jos'e A. Carrillo,et al.  A Review on Attractive–Repulsive Hydrodynamics for Consensus in Collective Behavior , 2016, 1605.00232.

[40]  Felipe Cucker,et al.  Modeling Language Evolution , 2004, Found. Comput. Math..

[41]  A. Bertozzi,et al.  State Transitions and the Continuum Limit for a 2D Interacting, Self-Propelled Particle System , 2006, nlin/0606031.

[42]  Felipe Cucker,et al.  Emergent Behavior in Flocks , 2007, IEEE Transactions on Automatic Control.

[43]  S. D. Flåm,et al.  Entropic Penalties in Finite Games , 2005, Ann. Oper. Res..

[44]  Singular vanishing-viscosity limits of gradient flows: the finite-dimensional case , 2016, 1611.08105.

[45]  Felipe Cucker,et al.  A General Collision-Avoiding Flocking Framework , 2011, IEEE Transactions on Automatic Control.

[46]  Jie Lin,et al.  Coordination of groups of mobile autonomous agents using nearest neighbor rules , 2003, IEEE Trans. Autom. Control..

[47]  Stefano Almi,et al.  Data-driven Evolutions of Critical Points , 2019, ArXiv.

[48]  Monika Sharma,et al.  Chemical oscillations , 2006 .

[49]  A. Czirók,et al.  Collective Motion , 1999, physics/9902023.

[50]  Fei Lu,et al.  Learning interaction kernels in heterogeneous systems of agents from multiple trajectories , 2019, J. Mach. Learn. Res..

[51]  Jie Lin,et al.  Correction to "Coordination of groups of mobile autonomous agents using nearest neighbor rules" , 2003, IEEE Trans. Autom. Control..

[52]  W. L. Romey.  Individual differences make a difference in the trajectories of simulated schools of fish , 1996 .

[53]  Arthur L. Koch,et al.  The social lifestyle of myxobacteria , 1999 .

[54]  Pierre Degond,et al.  Pedestrian Models based on Rational Behaviour , 2018, ArXiv.

[55]  Giang Tran,et al.  Exact Recovery of Chaotic Systems from Highly Corrupted Data , 2016, Multiscale Model. Simul..

[56]  P. Degond,et al.  A Hierarchy of Heuristic-Based Models of Crowd Dynamics , 2013, 1304.1927.

[57]  Alexandre B. Tsybakov,et al.  Introduction to Nonparametric Estimation , 2008, Springer series in statistics.

[58]  F. Cucker,et al.  Flocking in noisy environments , 2007, 0706.3343.

[59]  Ming Zhong,et al.  Nonparametric inference of interaction laws in systems of agents from trajectory data , 2018, Proceedings of the National Academy of Sciences.

[60]  V. Isaeva.  Self-organization in biological systems , 2012, Biology Bulletin.

[61]  Stephen P. Boyd,et al.  OSQP: an operator splitting solver for quadratic programs , 2017, 2018 UKACC 12th International Conference on Control (CONTROL).

[62]  P. Caines,et al.  Individual and mass behaviour in large population stochastic wireless power control problems: centralized and Nash equilibrium solutions , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[63]  Benedetto Piccoli,et al.  Modeling self-organization in pedestrians and animal groups from macroscopic and microscopic viewpoints , 2009, 0906.4702.

[64]  Naomi Ehrich Leonard,et al.  Virtual leaders, artificial potentials and coordinated control of groups , 2001, Proceedings of the 40th IEEE Conference on Decision and Control (Cat. No.01CH37228).

[65]  Mauro Maggioni,et al.  Data-driven Discovery of Emergent Behaviors in Collective Dynamics , 2020, Physica D. Nonlinear phenomena.

[66]  Peter E. Caines,et al.  Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle , 2006, Commun. Inf. Syst..

[67]  L. Edelstein-Keshet,et al.  Complexity, pattern, and evolutionary trade-offs in animal aggregation. , 1999, Science.

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

[69]  Steven V. Viscido,et al.  Self-Organized Fish Schools: An Examination of Emergent Properties , 2002, The Biological Bulletin.

[70]  Andrea L. Bertozzi,et al.  c ○ World Scientific Publishing Company A STATISTICAL MODEL OF CRIMINAL BEHAVIOR , 2008 .

[71]  Benedetto Piccoli,et al.  Multiscale Modeling of Granular Flows with Application to Crowd Dynamics , 2010, Multiscale Model. Simul..

[72]  Pedro Elosegui,et al.  Extension of the Cucker-Smale Control Law to Space Flight Formations , 2009 .

[73]  Rainer Hegselmann,et al.  Opinion dynamics and bounded confidence: models, analysis and simulation , 2002, J. Artif. Soc. Soc. Simul..

[74]  B. Piccoli,et al.  Multiscale Modeling of Pedestrian Dynamics , 2014 .

[75]  Patrick Kofod Mogensen,et al.  Optim: A mathematical optimization package for Julia , 2018, J. Open Source Softw..

[76]  Peter E. Caines,et al.  Mean Field Analysis of Controlled Cucker-Smale Type Flocking: Linear Analysis and Perturbation Equations , 2011 .