Restricted gradient-descent algorithm for value-function approximation in reinforcement learning

DOI10.1016/J.ARTINT.2007.08.001MaRDI QIDQ2389624zbMATH OpenOpenAlexFDO

Authors André da Motta Salles Barreto, Charles W. Anderson

Publication date 17 July 2009

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.artint.2007.08.001

zbMATH Keywords

neuro-dynamic programmingradial-basis-function networksreinforcement learningvalue-function approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Basis function adaptation in temporal difference reinforcement learning
• Reinforcement learning algorithms with function approximation: recent advances and applications
• Unsupervised basis function adaptation for reinforcement learning
• scientific article; zbMATH DE number 1946833
• Simple statistical gradient-following algorithms for connectionist reinforcement learning

Cites work

• 10.1162/1532443041827907
• \({\mathcal Q}\)-learning
• An analysis of temporal-difference learning with function approximation
• An upper bound on the loss from approximate optimal-value functions
• Basis function adaptation in temporal difference reinforcement learning
• Continuous-action Q-learning
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Evolution strategies. A comprehensive introduction
• Feature-based methods for large scale dynamic programming
• scientific article; zbMATH DE number 3126094 (Why is no real title available?)
• scientific article; zbMATH DE number 3128787 (Why is no real title available?)
• scientific article; zbMATH DE number 3168214 (Why is no real title available?)
• scientific article; zbMATH DE number 4040466 (Why is no real title available?)
• scientific article; zbMATH DE number 4061056 (Why is no real title available?)
• scientific article; zbMATH DE number 4074523 (Why is no real title available?)
• scientific article; zbMATH DE number 20218 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 2086450 (Why is no real title available?)
• scientific article; zbMATH DE number 2087264 (Why is no real title available?)
• Intelligent control for an acrobot
• Kernel-based reinforcement learning
• Linear least-squares algorithms for temporal difference learning
• Networks and the best approximation property
• On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• On the convergence of temporal-difference learning with linear function approximation
• Reinforcement learning with replacing eligibility traces
• Solving factored mdps with hybrid state and action variables
• Technical update: Least-squares temporal difference learning

Cited in

(2)

• Estimation and approximation bounds for gradient-based reinforcement learning
• Value iteration for streaming data on a continuous space with gradient method in an RKHS

Describes a project that uses

Uses Software

• EOlib

This page was built for publication: Restricted gradient-descent algorithm for value-function approximation in reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2389624)