Asynchronous stochastic approximation with differential inclusions

DOI10.1214/11-SSY056zbMath1311.62125arXiv1112.2288OpenAlexW1998587447MaRDI QIDQ5168859

David S. Leslie, Steven Perkins

Publication date: 21 July 2014

Full work available at URL: https://arxiv.org/abs/1112.2288

zbMATH Keywords

differential inclusionasynchronous stochastic approximationset-valued mean fieldtwo-timescales

Mathematics Subject Classification ID

Martingales with discrete parameter (60G42) Lyapunov and storage functions (93D30) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic approximation (62L20)

Related Items (9)

Penalty-Regulated Dynamics and Robust Learning Procedures in Games ⋮ Reference points and learning ⋮ Stochastic recursive inclusions with non-additive iterate-dependent Markov noise ⋮ Robustness Properties in Fictitious-Play-Type Algorithms ⋮ Stochastic approximation with discontinuous dynamics, differential inclusions, and applications ⋮ Independent learning in stochastic games ⋮ Learning in games with continuous action sets and unknown payoff functions ⋮ Q-learning for Markov decision processes with a satisfiability criterion ⋮ Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise

Cites Work

• Unnamed Item
• Unnamed Item
• Stabilization of stochastic approximation by step size adaptation
• Stochastic approximation. A dynamical systems viewpoint.
• Stochastic approximation methods for constrained and unconstrained systems
• Asynchronous stochastic approximation and Q-learning
• Stochastic approximation with two time scales
• Convergent multiple-timescales reinforcement learning algorithms in normal form games
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
• Stochastic approximation with `controlled Markov' noise
• Stochastic approximations for finite-state Markov chains
• Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms
• Stochastic approximation algorithms for parallel and distributed processing
• Analysis of recursive stochastic algorithms
• Asynchronous Stochastic Approximations
• OnActor-Critic Algorithms
• A Dynamical System Approach to Stochastic Approximations
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Stochastic Approximations and Differential Inclusions
• Stochastic Approximations and Differential Inclusions, Part II: Applications
• On the Theory of Dynamic Programming
• Viability theory

This page was built for publication: Asynchronous stochastic approximation with differential inclusions