Stochastic Approximations and Differential Inclusions

DOI10.1137/S0363012904439301zbMath1087.62091OpenAlexW1964757264MaRDI QIDQ5317133

Michel Benaïm, Josef Hofbauer, Sylvain Sorin

Publication date: 15 September 2005

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/s0363012904439301

zbMATH Keywords

game theorydifferential inclusionslearningapproachabilityfictitious playset-valued dynamical systemschain recurrence

Mathematics Subject Classification ID

Stability of topological dynamical systems (37B25) Ordinary differential inclusions (34A60) Evolution inclusions (34G25) Stochastic approximation (62L20) Ordinary differential equations and systems with randomness (34F05) Rationality and learning in game theory (91A26) Evolutionary games (91A22)

Related Items (81)

On the robustness of learning in games with stochastically perturbed payoff observations ⋮ Approachability in population games ⋮ Replicator dynamics: old and new ⋮ Conley index theory and the attractor-repeller decomposition for differential inclusions ⋮ On Best-Response Dynamics in Potential Games ⋮ Multiscale Q-learning with linear function approximation ⋮ Consensus in opinion dynamics as a repeated game ⋮ Asynchronous stochastic approximation with differential inclusions ⋮ Convergence of constant step stochastic gradient descent for non-smooth non-convex functions ⋮ Stochastic Methods for Composite and Weakly Convex Optimization Problems ⋮ Distributed Stochastic Approximation with Local Projections ⋮ Unnamed Item ⋮ Perturbations of set-valued dynamical systems, with applications to game theory ⋮ Stochastic recursive inclusions with non-additive iterate-dependent Markov noise ⋮ Constant step stochastic approximations involving differential inclusions: stability, long-run convergence and applications ⋮ Fictitious Play in Zero-Sum Stochastic Games ⋮ Adaptation, coordination, and local interactions via distributed approachability ⋮ Sampling best response dynamics and deterministic equilibrium selection ⋮ Robustness Properties in Fictitious-Play-Type Algorithms ⋮ Corrigendum to: ``Asymptotic behavior of Bayesian learners with misspecified models ⋮ Lyapunov stability of the subgradient method with constant step size ⋮ Mean field games on prosumers ⋮ Stochastic fictitious play with continuous action sets ⋮ Stochastic proximal subgradient descent oscillates in the vicinity of its accumulation set ⋮ Subgradient Sampling for Nonsmooth Nonconvex Minimization ⋮ On set-valued discrete dynamical systems ⋮ Stochastic approximation with discontinuous dynamics, differential inclusions, and applications ⋮ Affine Relaxations of the Best Response Algorithm: Global Convergence in Ratio-Bounded Games ⋮ No-regret algorithms in on-line learning, games and convex optimization ⋮ Evolutionary dynamics in heterogeneous populations: a general framework for an arbitrary type distribution ⋮ Pathological Subgradient Dynamics ⋮ Smale strategies for network prisoner's dilemma games ⋮ Continuous time learning algorithms in optimization and game theory ⋮ Conservative parametric optimality and the ridge method for tame min-max problems ⋮ Continuous Newton-like Methods Featuring Inertia and Variable Mass ⋮ Independent learning in stochastic games ⋮ Convergence in games with continua of equilibria ⋮ Implementing biological hybrid systems: allowing composition and avoiding stiffness ⋮ Asymptotic bias of stochastic gradient search ⋮ Approachability in Stackelberg stochastic games with vector costs ⋮ Dynamics in near-potential games ⋮ Best-response dynamics in zero-sum stochastic games ⋮ Regular potential games ⋮ Why learning doesn't add up: Equilibrium selection with a composition of learning rules ⋮ Two more classes of games with the continuous-time fictitious play property ⋮ Preface: Special issue in honor of the 60th birthday of Sylvain Sorin ⋮ Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization ⋮ Qualitative properties of certain piecewise deterministic Markov processes ⋮ ERGODIC PROPERTIES OF WEAK ASYMPTOTIC PSEUDOTRAJECTORIES FOR SET-VALUED DYNAMICAL SYSTEMS ⋮ Vertex reinforced non-backtracking random walks: an example of path formation ⋮ Q-learning for Markov decision processes with a satisfiability criterion ⋮ Exponential weight algorithm in continuous time ⋮ Stability in games with continua of equilibria ⋮ Learning in games with unstable equilibria ⋮ Stochastic approximation on Riemannian manifolds ⋮ Fictitious play in \(3 \times 3\) games: chaos and dithering behaviour ⋮ A Robust Saturated Strategy for $n$-Player Prisoner's Dilemma ⋮ Stochastic approximation with `controlled Markov' noise ⋮ A payoff-based learning procedure and its application to traffic games ⋮ Generalised weakened fictitious play ⋮ Dynamical behavior of a stochastic forward-backward algorithm using random monotone operators ⋮ Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning ⋮ Stochastic subgradient method converges on tame functions ⋮ Asymptotic behavior of Bayesian learners with misspecified models ⋮ Incremental without replacement sampling in nonconvex optimization ⋮ Solvability of fractional differential inclusion with a generalized Caputo derivative ⋮ Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning ⋮ Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise ⋮ Asymptotic equivalence of evolution equations governed by cocoercive operators and their forward discretizations ⋮ Game-Theoretic Learning and Allocations in Robust Dynamic Coalitional Games ⋮ An Inertial Newton Algorithm for Deep Learning ⋮ Learning in Games via Reinforcement and Regularization ⋮ An ODE method to prove the geometric convergence of adaptive stochastic algorithms ⋮ A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization ⋮ Multi-agent reinforcement learning: a selective overview of theories and algorithms ⋮ Distributed stochastic nonsmooth nonconvex optimization ⋮ Tributes to Bill Sandholm ⋮ Learning in nonatomic games. I: Finite action spaces and population games ⋮ Equilibrium routing under uncertainty ⋮ Analyzing Approximate Value Iteration Algorithms ⋮ ON FRACTIONAL DIFFERENTIAL INCLUSION PROBLEMS INVOLVING FRACTIONAL ORDER DERIVATIVE WITH RESPECT TO ANOTHER FUNCTION

This page was built for publication: Stochastic Approximations and Differential Inclusions