Boundedness of iterates in Q-learning

DOI10.1016/J.SYSCONLE.2005.08.011MaRDI QIDQ2504669zbMATH OpenOpenAlexFDO

Authors Abhijit Gosavi

Publication date 25 September 2006

Published in Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.sysconle.2005.08.011

zbMATH Keywords

boundednessq-learningstochastic control

Mathematics Subject Classification ID

Stochastic programming (90C15) Dynamic programming (90C39) Stochastic learning and adaptive control (93E35)

Recommendations

• On boundedness of Q-learning iterates for stochastic shortest path problems
• Error bounds for constant step-size \(Q\)-learning
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• Asynchronous stochastic approximation and Q-learning
• Convergence of discretization procedure in Q-learning

Cites work

• A Stochastic Approximation Method
• Asynchronous stochastic approximation and Q-learning
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning

Cited in

(11)

• Error bounds for constant step-size \(Q\)-learning
• Reference points and learning
• An information-theoretic analysis of return maximization in reinforcement learning
• Attainability of boundary points under reinforcement learning
• Convergence of discretization procedure in Q-learning
• On boundedness of Q-learning iterates for stochastic shortest path problems
• \(Q\)-learning in a stochastic Stackelberg game between an uninformed leader and a naive follower
• A Discrete-Time Switching System Analysis of Q-Learning
• Deep reinforcement learning for approximate policy iteration: convergence analysis and a post-earthquake disaster response case study
• Concentration of contractive stochastic approximation: additive and multiplicative noise
• Q-learning algorithms with random truncation bounds and applications to effective parallel computing

This page was built for publication: Boundedness of iterates in \(Q\)-learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2504669)