Kernel-based reinforcement learning in average-cost problems

DOI10.1109/TAC.2002.803530MaRDI QIDQ5267044zbMATH OpenOpenAlexFDO

Authors Dirk Ormoneit, Peter W. Glynn

Publication date 20 June 2017

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

Full work available at URL https://doi.org/10.1109/tac.2002.803530

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Least squares and related methods for stochastic control systems (93E24)

Cited in

(10)

• Hoeffding's inequality for uniformly ergodic Markov chains
• An algorithmic approach to optimal asset liquidation problems
• Average cost temporal-difference learning
• Efficient algorithms of pathwise dynamic programming for decision optimization in mining operations
• Kernel dynamic policy programming: applicable reinforcement learning to robot systems with high dimensional states
• Algorithms for optimal control of stochastic switching systems
• Mean-field controls with Q-learning for cooperative MARL: convergence and complexity analysis
• On Hoeffding and Bernstein type inequalities for sums of random variables in non-additive measure spaces and complete convergence
• Hoeffding's inequality for non-irreducible Markov models
• Approximated multi-agent fitted Q iteration

This page was built for publication: Kernel-based reinforcement learning in average-cost problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5267044)