Learning in nonatomic games. I: Finite action spaces and population games
From MaRDI portal
Publication:2106066
DOI10.3934/JDG.2022018zbMATH Open1503.91014arXiv2107.01595OpenAlexW3178113021MaRDI QIDQ2106066FDOQ2106066
Authors: Saeed Hadikhanloo, Rida Laraki, Panayotis Mertikopoulos, Sylvain Sorin 
Publication date: 8 December 2022
Published in: Journal of Dynamics and Games (Search for Journal in Brave)
Abstract: We examine the long-run behavior of a wide range of dynamics for learning in nonatomic games, in both discrete and continuous time. The class of dynamics under consideration includes fictitious play and its regularized variants, the best-reply dynamics (again, possibly regularized), as well as the dynamics of dual averaging / "follow the regularized leader" (which themselves include as special cases the replicator dynamics and Friedman's projection dynamics). Our analysis concerns both the actual trajectory of play and its time-average, and we cover potential and monotone games, as well as games with an evolutionarily stable state (global or otherwise). We focus exclusively on games with finite action spaces; nonatomic games with continuous action spaces are treated in detail in Part II of this paper.
Full work available at URL: https://arxiv.org/abs/2107.01595
Recommendations
learningdual averagingNash equilibriumvariational inequalitiesevolutionary stabilityfictitious playnonatomic games
Games with infinitely many players (91A07) Evolutionary games (91A22) Rationality and learning in game theory (91A26)
Cites Work
- Primal-dual subgradient methods for convex problems
- Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
- Evolutionarily stable strategies and game dynamics
- Title not available (Why is that?)
- The logic of animal conflict
- On the generalization of a direct method of the calculus of variations
- Potential games
- Optimal properties of stimulus-response learning models.
- Quantal response equilibria for normal form games
- Stable games and their dynamics
- On the robustness of learning in games with stochastically perturbed payoff observations
- Finite composite games: equilibria and dynamics
- Online learning and online convex optimization
- Time Average Replicator and Best-Reply Dynamics
- Social Stability and Equilibrium
- Evolutionary game dynamics
- Title not available (Why is that?)
- Potential games with continuous player sets
- Dual extrapolation and its applications to solving variational inequalities and related problems
- Exponential weight algorithm in continuous time
- The emergence of rational behavior in the presence of stochastic perturbations
- Evolutionary Games in Economics
- Solving variational inequalities with stochastic mirror-prox algorithm
- Fictitious play property for games with identical interests
- An iterative method of solving a game
- Evolutionarily stable strategies with two types of player
- On the Global Convergence of Stochastic Fictitious Play
- Conditional universal consistency.
- Equilibrium points of nonatomic games
- Convex analysis and monotone operator theory in Hilbert spaces
- Stochastic Approximations and Differential Inclusions
- Stochastic Approximations and Differential Inclusions, Part II: Applications
- On a theorem of Schmeidler
- Title not available (Why is that?)
- Title not available (Why is that?)
- Consistency of vanishingly smooth fictitious play
- A continuous-time approach to online optimization
- Riemannian game dynamics
- Learning in games with continuous action sets and unknown payoff functions
- Learning in games via reinforcement and regularization
- On the convergence of gradient-like flows with noisy gradient input
- Replicator dynamics: old and new
Cited In (17)
- Stochastic Learning Dynamics and Speed of Convergence in Population Games
- Approachability in population games
- Learning correlated equilibria in population games.
- Title not available (Why is that?)
- Learning in games with continuous action sets and unknown payoff functions
- Penalty-regulated dynamics and robust learning procedures in games
- Nested replicator dynamics, nested logit choice, and similarity-based learning
- A link between sequential semi-anonymous nonatomic games and their large finite counterparts
- Learning in games via reinforcement and regularization
- Multiagent Online Learning in Time-Varying Games
- Stochastic fictitious play with continuous action sets
- Continuous time learning algorithms in optimization and game theory
- Regularized Bayesian best response learning in finite games
- Learning in mean field games: The fictitious play
- Learning in games by random sampling
- Learning and Efficiency in Games with Dynamic Population
- Dynamics in near-potential games
This page was built for publication: Learning in nonatomic games. I: Finite action spaces and population games
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2106066)
