Serial and parallel value iteration algorithms for discounted Markov decision processes

DOI10.1016/0377-2217(93)90061-QzbMath0791.90067MaRDI QIDQ2367364

Thomas W. Archibald, K. I. M. McKinnon, Lyn C. Thomas

Publication date: 13 July 1994

Published in: European Journal of Operational Research (Search for Journal in Brave)

zbMATH Keywords

parallel implementationtransputersdiscounted Markov decision processesserial value iteration schemesstate space partition

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Parallel numerical computation (65Y05)

Related Items (1)

Optimizing Long‐term Hydro‐power Production Using Markov Decision Processes

Cites Work

• Unnamed Item
• Unnamed Item
• Computational comparison of value iteration algorithms for discounted Markov decision processes
• On iterative optimization ol structured Markov decision processes with discounted rewards
• Computing the discounted return in markov and semi-markov chains
• Improved iterative computation of the expected discounted return in Markov and semi-Markov chains
• Discounting, Ergodicity and Convergence for Markov Decision Processes
• On the Generation of Markov Decision Processes
• Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
• Some Bounds for Discounted Sequential Decision Processes

This page was built for publication: Serial and parallel value iteration algorithms for discounted Markov decision processes