Model-based reinforcement learning with dimension reduction

DOI10.1016/J.NEUNET.2016.08.005MaRDI QIDQ2281680zbMATH OpenOpenAlexWikidataFDO

Authors Voot Tangkaratt, Jun Morimoto, Masashi Sugiyama

Publication date 6 January 2020

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2016.08.005

zbMATH Keywords

model-based reinforcement learningsufficient dimension reductiontransition model estimation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation
• Dimension reduction and its application to model-based exploration in continuous spaces
• 10.1162/1532443041827907
• Automatic complexity reduction in reinforcement learning
• scientific article; zbMATH DE number 2087264

Cites work

• A constructive approach to the estimation of dimension reduction directions
• Analysis and improvement of policy gradient estimation
• Conditional density estimation with dimensionality reduction via squared-loss conditional entropy minimization
• Efficient sample reuse in policy gradients with parameter-based exploration
• Gaussian processes for machine learning.
• Gradient-based kernel dimension reduction for regression
• scientific article; zbMATH DE number 1753152 (Why is no real title available?)
• scientific article; zbMATH DE number 5223994 (Why is no real title available?)
• Kernel dimension reduction in regression
• Learning from examples with information theoretic criteria
• Manopt, a Matlab toolbox for optimization on manifolds
• Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation
• Save: a method for dimension reduction and graphics in regression
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Sliced Inverse Regression for Dimension Reduction
• Sufficient Dimension Reduction via Inverse Regression
• Sufficient dimension reduction via squared-loss mutual information estimation
• Theory of Reproducing Kernels

Cited in

(5)

• General value iteration based single network approach for constrained optimal controller design of partially-unknown continuous-time nonlinear systems
• Dimension reduction and its application to model-based exploration in continuous spaces
• An adaptive deep Q-learning strategy for handwritten digit recognition
• scientific article; zbMATH DE number 7306889 (Why is no real title available?)
• Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation

Describes a project that uses

Uses Software

• Manopt

This page was built for publication: Model-based reinforcement learning with dimension reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2281680)