Policy Evaluation in Continuous MDPs With Efficient Kernelized Gradient Temporal Difference

DOI10.1109/TAC.2020.3029315MaRDI QIDQ4990298zbMATH OpenFDO

Authors

Publication date 28 May 2021

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1709.04221

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Cited in

(6)

• Kernel dynamic policy programming: applicable reinforcement learning to robot systems with high dimensional states
• scientific article; zbMATH DE number 6860770 (Why is no real title available?)
• On the sample complexity of actor-critic method for reinforcement learning with function approximation
• Policy Evaluation in Continuous MDPs with Efficient Kernelized Gradient Temporal Difference
• Optimal policy evaluation using kernel-based temporal difference methods
• Reinforcement learning for infinite-dimensional systems

This page was built for publication: Policy Evaluation in Continuous MDPs With Efficient Kernelized Gradient Temporal Difference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4990298)