Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms

DOI10.1137/S0363012998346621zbMath1063.62567OpenAlexW2150123286MaRDI QIDQ4537821

Jinane Abounadi, Dimitri P. Bertsekas, Vivek S. Borkar

Publication date: 23 June 2002

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

Full work available at URL: https://doi.org/10.1137/s0363012998346621

zbMATH Keywords

stochastic approximation\(Q\)-learningneuro-dynamic programming

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic approximation (62L20)

Related Items (13)

Some Limit Properties of Markov Chains Induced by Recursive Stochastic Algorithms ⋮ Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design ⋮ Stochastic approximation with long range dependent and heavy tailed noise ⋮ Risk-Sensitive Reinforcement Learning via Policy Gradient Search ⋮ Stochastic Fixed-Point Iterations for Nonexpansive Maps: Convergence and Error Bounds ⋮ Stabilization of stochastic approximation by step size adaptation ⋮ Technical Note—Consistency Analysis of Sequential Learning Under Approximate Bayesian Inference ⋮ Reinforcement learning for long-run average cost. ⋮ Continuous-Time Robust Dynamic Programming ⋮ On the convergence of stochastic approximations under a subgeometric ergodic Markov dynamic ⋮ Empirical Q-Value Iteration ⋮ Analyzing Approximate Value Iteration Algorithms ⋮ Concentration of Contractive Stochastic Approximation and Reinforcement Learning

This page was built for publication: Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms