Stochastic Approximations and Differential Inclusions, Part II: Applications

DOI10.1287/moor.1060.0213zbMath1284.62511OpenAlexW2168635421MaRDI QIDQ5388003

Sylvain Sorin, Michel Benaïm, Josef Hofbauer

Publication date: 27 May 2008

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/moor.1060.0213

zbMATH Keywords

differential inclusionsconsistencystochastic approximationapproachabilityset-valued dynamical systemsno regretsmooth fictitious play

Mathematics Subject Classification ID

Ordinary differential inclusions (34A60) Stochastic approximation (62L20) Dynamic games (91A25) Rationality and learning in game theory (91A26) Boundary value problems on infinite intervals for ordinary differential equations (34B40)

Related Items (29)

Replicator dynamics: old and new ⋮ Multiscale Q-learning with linear function approximation ⋮ Consensus in opinion dynamics as a repeated game ⋮ Asynchronous stochastic approximation with differential inclusions ⋮ Perturbations of set-valued dynamical systems, with applications to game theory ⋮ Constant step stochastic approximations involving differential inclusions: stability, long-run convergence and applications ⋮ Adaptation, coordination, and local interactions via distributed approachability ⋮ A stochastic variant of replicator dynamics in zero-sum games and its invariant measures ⋮ Pathological Subgradient Dynamics ⋮ Continuous time learning algorithms in optimization and game theory ⋮ Approachability in Stackelberg stochastic games with vector costs ⋮ Approachability, regret and calibration: implications and equivalences ⋮ The dynamic instability of dispersed price equilibria ⋮ Stochastic learning in multi-agent optimization: communication and payoff-based approaches ⋮ Preface: Special issue in honor of the 60th birthday of Sylvain Sorin ⋮ ERGODIC PROPERTIES OF WEAK ASYMPTOTIC PSEUDOTRAJECTORIES FOR SET-VALUED DYNAMICAL SYSTEMS ⋮ Q-learning for Markov decision processes with a satisfiability criterion ⋮ A continuous-time approach to online optimization ⋮ Risk-Constrained Reinforcement Learning with Percentile Risk Criteria ⋮ Exponential weight algorithm in continuous time ⋮ Networks of biosensors: decentralized activation and social learning ⋮ Boundary value problems for \(q\)-difference inclusions ⋮ Existence results for boundary value problems of differential inclusions with three-point integral boundary conditions ⋮ Stochastic subgradient method converges on tame functions ⋮ An ODE method to prove the geometric convergence of adaptive stochastic algorithms ⋮ Learning Correlated Equilibria in Noncooperative Games with Cluster Structure ⋮ A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization ⋮ Learning in nonatomic games. I: Finite action spaces and population games ⋮ Equilibrium routing under uncertainty

This page was built for publication: Stochastic Approximations and Differential Inclusions, Part II: Applications