Asynchronous stochastic approximation with applications to average-reward reinforcement learning

DOI10.1137/25M1769806MaRDI QIDQ7257404zbMATH OpenFDO

Authors Huizhen Yu, Yi Wan, Richard S. Sutton

Publication date 4 June 2026

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

Full work available at URL https://doi.org/10.1137/25M1769806

zbMATH Keywords

stability and convergenceasynchronous stochastic approximationshadowing propertiesaverage-reward reinforcement learningMarkov and semi-Markov decision processes

Mathematics Subject Classification ID

Stochastic approximation (62L20) Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Cites work

• scientific article; zbMATH DE number 1183917 (Why is no real title available?)
• scientific article; zbMATH DE number 3723610 (Why is no real title available?)
• scientific article; zbMATH DE number 3538599 (Why is no real title available?)
• scientific article; zbMATH DE number 3616736 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 515776 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 1972910 (Why is no real title available?)
• scientific article; zbMATH DE number 1405930 (Why is no real title available?)
• A Dynamical System Approach to Stochastic Approximations
• Asymptotic pseudotrajectories and chain recurrent flows, with applications
• Asynchronous Stochastic Approximations
• Asynchronous Stochastic Approximations With Asymptotically Biased Errors and Deep Multiagent Learning
• Asynchronous stochastic approximation and Q-learning
• Dynamic programming, Markov chains, and the method of successive approximations
• Iterative solution of the functional equations of undiscounted Markov renewal programming
• Learning algorithms for Markov decision processes with average cost
• On boundedness of Q-learning iterates for stochastic shortest path problems
• Stability theory of dynamical systems.
• Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms
• The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems
• The Borkar-Meyn theorem for asynchronous stochastic approximations
• The Functional Equations of Undiscounted Markov Renewal Programming
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• -limit sets for axiom A diffeomorphisms

This page was built for publication: Asynchronous stochastic approximation with applications to average-reward reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7257404)