A note on policy algorithms for discounted Markov decision problems

DOI10.1016/S0167-6377(99)00051-6zbMath0937.90117OpenAlexW2011074416WikidataQ115027952 ScholiaQ115027952MaRDI QIDQ1969768

Michael Kwok-Po Ng

Publication date: 19 March 2000

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0167-6377(99)00051-6

zbMATH Keywords

matricesdiscounted Markov decision processpolicy algorithm

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (2)

Markov control processes with randomized discounted cost ⋮ A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases

Cites Work

• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Unnamed Item

This page was built for publication: A note on policy algorithms for discounted Markov decision problems