NDP methods for multi-chain MDPs

DOI10.1007/978-3-540-37258-5_151MaRDI QIDQ3063272zbMATH OpenOpenAlexFDO

Authors Hao Tang, Lei Zhou, Arai Tamio

Publication date 30 December 2010

Published in Intelligent Computing in Signal Processing and Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-540-37258-5_151

zbMATH Keywords

multichain Markov decision processesneuro-dynamic programming method

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Approximation methods and heuristics in mathematical programming (90C59)

Recommendations

• A unified NDP method for SMDP by an actor network
• Unified NDP method based on TD(0) learning for both average and discounted Markov decision processes
• A Rollout Algorithm for Multichain Markov Decision Processes with Average Cost
• Simulation-based algorithms for Markov decision processes.
• A survey of some simulation-based algorithms for Markov decision processes

Cited in

(2)

• A unified NDP method for SMDP by an actor network
• Unified NDP method based on TD(0) learning for both average and discounted Markov decision processes

This page was built for publication: NDP methods for multi-chain MDPs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3063272)