Maximal Average-Reward Policies for Semi-Markov Decision Processes With Arbitrary State and Action Space
From MaRDI portal
Publication:5639542
DOI10.1214/aoms/1177693170zbMath0231.90057OpenAlexW2017531590WikidataQ114846540 ScholiaQ114846540MaRDI QIDQ5639542
Publication date: 1971
Published in: The Annals of Mathematical Statistics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1214/aoms/1177693170
Markov renewal processes, semi-Markov processes (60K15) Markov and semi-Markov decision processes (90C40)
Related Items (7)
\(\epsilon\)-forced adaptive policy in age replacement ⋮ A semi-Markov inventory control model ⋮ Semi-Markov decision processes with a reachable state-subset ⋮ Semi-Markov processes and their applications ⋮ On the optimal control of a class of continuous time non-Markov decision processes ⋮ Semi-Markov decision processes with vector pay-offs ⋮ Long-term average cost control problems for continuous time Markov processes: A survey
This page was built for publication: Maximal Average-Reward Policies for Semi-Markov Decision Processes With Arbitrary State and Action Space
