Potential-Based Online Policy Iteration Algorithms for Markov Decision Processes

DOI10.1109/TAC.2004.825647MaRDI QIDQ5273720zbMATH OpenWikidataFDO

Authors Hai-Tao Fang, Cao, Xiren

Publication date 12 July 2017

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

Full work available at URL https://doi.org/10.1109/TAC.2004.825647

Mathematics Subject Classification ID

Markov renewal processes, semi-Markov processes (60K15) Applications of Markov renewal processes (reliability, queueing networks, etc.) (60K20) Markov and semi-Markov decision processes (90C40)

Cited in

(9)

• Basic ideas for event-based optimization of Markov systems
• Early developments of control theory in China
• Simple regret optimization in online planning for Markov decision processes
• A performance gradient perspective on gradient‐based policy iteration and a modified value iteration
• Look-ahead control of conveyor-serviced production station by using potential-based online policy iteration
• Finding optimal memoryless policies of POMDPs under the expected average reward criterion
• Temporal difference-based policy iteration for optimal control of stochastic systems
• An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions
• Point-Based Online Value Iteration Algorithm for POMDPs

This page was built for publication: Potential-Based Online Policy Iteration Algorithms for Markov Decision Processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5273720)