Inertial game dynamics and applications to constrained optimization
From MaRDI portal
folk theoremgame dynamicsHessian-Riemannian metricslearningreplicator dynamicssecond-order dynamicsstability of equilibriawell-posedness
Initial value problems, existence, uniqueness, continuous dependence and continuation of solutions to ordinary differential equations (34A12) Geometric methods in ordinary differential equations (34A26) Asymptotic properties of solutions to ordinary differential equations (34D05) Convex programming (90C25) Methods of reduced gradient type (90C52) Evolutionary games (91A22) Rationality and learning in game theory (91A26) Other game-theoretic models (91A40)
Abstract: Aiming to provide a new class of game dynamics with good long-term rationality properties, we derive a second-order inertial system that builds on the widely studied "heavy ball with friction" optimization method. By exploiting a well-known link between the replicator dynamics and the Shahshahani geometry on the space of mixed strategies, the dynamics are stated in a Riemannian geometric framework where trajectories are accelerated by the players' unilateral payoff gradients and they slow down near Nash equilibria. Surprisingly (and in stark contrast to another second-order variant of the replicator dynamics), the inertial replicator dynamics are not well-posed; on the other hand, it is possible to obtain a well-posed system by endowing the mixed strategy space with a different Hessian-Riemannian (HR) metric structure, and we characterize those HR geometries that do so. In the single-agent version of the dynamics (corresponding to constrained optimization over simplex-like objects), we show that regular maximum points of smooth functions attract all nearby solution orbits with low initial speed. More generally, we establish an inertial variant of the so-called "folk theorem" of evolutionary game theory and we show that strict equilibria are attracting in asymmetric (multi-population) games - provided of course that the dynamics are well-posed. A similar asymptotic stability result is obtained for evolutionarily stable strategies in symmetric (single- population) games.
Recommendations
Cites work
- ``Evolutionary selection dynamic in games: Convergence and limit properties
- A new mathematical framework for the study of linkage and selection
- A second-order gradient-like dissipative dynamical system with Hessian-driven damping. Application to optimization and mechanics.
- Adaptive dynamics and evolutionary stability
- Barrier Operators and Associated Gradient-Like Dynamical Systems for Constrained Minimization Problems
- Convergence of solutions to second-order gradient-like systems with analytic nonlinearities
- Convex Analysis
- Domination or equilibrium
- Evolutionarily stable strategies and game dynamics
- Evolutionarily stable strategies with two types of player
- Evolutionary dynamics for bimatrix games: A Hamiltonian system?
- Evolutionary game dynamics
- Evolutionary Games and Population Dynamics
- Evolutionary Games in Economics
- Evolutionary stability in asymmetric games
- Exponential weight algorithm in continuous time
- Hessian Riemannian Gradient Flows in Convex Programming
- Higher order game dynamics
- scientific article; zbMATH DE number 4015993 (Why is no real title available?)
- scientific article; zbMATH DE number 5869530 (Why is no real title available?)
- scientific article; zbMATH DE number 4141836 (Why is no real title available?)
- scientific article; zbMATH DE number 3683431 (Why is no real title available?)
- scientific article; zbMATH DE number 3790208 (Why is no real title available?)
- scientific article; zbMATH DE number 679849 (Why is no real title available?)
- scientific article; zbMATH DE number 1077335 (Why is no real title available?)
- scientific article; zbMATH DE number 903638 (Why is no real title available?)
- scientific article; zbMATH DE number 917233 (Why is no real title available?)
- scientific article; zbMATH DE number 1405930 (Why is no real title available?)
- Learning in games via reinforcement and regularization
- On Hessian Riemannian structures
- On the Minimizing Property of a Second Order Dissipative System in Hilbert Spaces
- Online learning and online convex optimization
- Optimal properties of stimulus-response learning models.
- Penalty-regulated dynamics and robust learning procedures in games
- Perturbed variations of penalty function methods. Example: Projective SUMT
- Potential games
- Potential games with continuous player sets
- Primal-dual subgradient methods for convex problems
- Quantal response equilibria for normal form games
- Symmetric spaces with invariant locally Hessian structures
- The emergence of rational behavior in the presence of stochastic perturbations
- THE HEAVY BALL WITH FRICTION METHOD, I. THE CONTINUOUS DYNAMICAL SYSTEM: GLOBAL EXPLORATION OF THE LOCAL MINIMA OF A REAL-VALUED FUNCTION BY ASYMPTOTIC ANALYSIS OF A DISSIPATIVE DYNAMICAL SYSTEM
- The logic of animal conflict
- The Nonlinear Geometry of Linear Programming. I Affine and Projective Scaling Trajectories
- The Projective SUMT Method for Convex Programming
- The weighted majority algorithm
Cited in
(8)- Riemannian game dynamics
- Imitation dynamics with payoff shocks
- Learning in games via reinforcement and regularization
- Penalty-regulated dynamics and robust learning procedures in games
- scientific article; zbMATH DE number 7363383 (Why is no real title available?)
- scientific article; zbMATH DE number 223254 (Why is no real title available?)
- Generalized momentum-based methods: a Hamiltonian perspective
- Lyapunov functions for time-scale dynamics on Riemannian geometries of the simplex
This page was built for publication: Inertial game dynamics and applications to constrained optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3195290)
