Nonparametric approximation generalized policy iteration reinforcement learning algorithm based on states clustering

DOI10.13195/J.KZYJC.2016.1148MaRDI QIDQ4574671zbMATH OpenFDO

Authors Ting Ji, Hua Zhang

Publication date 18 July 2018

zbMATH Keywords

reinforcement learningpolicy iterationnonparametric approximationstates clustering

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Non-parametric policy search with limited information loss
• Rollout sampling approximate policy iteration
• Regularized policy iteration with nonparametric function spaces
• Reinforcement learning method of continuous state adaptively discretized based on \(K\)-means clustering
• Parametric Approximation Policy Iteration Algorithm Based on Gaussian Process

Cited in

(1)

• Reinforcement learning method of continuous state adaptively discretized based on \(K\)-means clustering

This page was built for publication: Nonparametric approximation generalized policy iteration reinforcement learning algorithm based on states clustering

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4574671)