Hessian matrix distribution for Bayesian policy gradient reinforcement learning

DOI10.1016/J.INS.2011.01.001MaRDI QIDQ545311zbMATH OpenOpenAlexFDO

Authors Ngo Anh Vien, Hwanjo Yu, TaeChoong Chung

Publication date 22 June 2011

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2011.01.001

zbMATH Keywords

Markov decision processreinforcement learningBayesian policy gradientHessian matrix distributionMonte-Carlo policy gradientpolicy gradient

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Bayesian policy gradient and actor-critic algorithms
• Using Gaussian processes for variance reduction in policy gradient algorithms
• Approximate Newton Policy Gradient Algorithms
• Expected policy gradients for reinforcement learning
• Analysis and improvement of policy gradient estimation

Cites work

• scientific article; zbMATH DE number 5957269 (Why is no real title available?)
• scientific article; zbMATH DE number 3126094 (Why is no real title available?)
• scientific article; zbMATH DE number 51536 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 1753152 (Why is no real title available?)
• A generic architecture for adaptive agents based on reinforcement learning
• Adaptive evolutionary programming based on reinforcement learning
• Adaptive stock trading with dynamic asset allocation using reinforcement learning
• Bayes-Hermite quadrature
• Bayesian policy gradient and actor-critic algorithms
• Fuzzy control rules extraction from perception-based information using computing with words
• Natural actor-critic algorithms

Cited in

(1)

• Policy sharing between multiple mobile robots using decision trees

This page was built for publication: Hessian matrix distribution for Bayesian policy gradient reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q545311)