Successive approximations for Markov decision processes and Markov games with unbounded rewards

DOI10.1080/02331937908842597zbMath0421.90075OpenAlexW2128640948MaRDI QIDQ3854944

Jaap Wessels, J. A. E. E. Van Nunen

Publication date: 1979

Published in: Mathematische Operationsforschung und Statistik. Series Optimization (Search for Journal in Brave)

Full work available at URL: https://research.tue.nl/nl/publications/d9fad78f-5659-4e06-88af-6acf3ea2640c

zbMATH Keywords

convergenceMarkov decision processessuccessive approximationsMarkov gamesunbounded rewards

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) 2-person games (91A05)

Related Items

The numerical exploitation of periodicity in Markov decision processes ⋮ On theory and algorithms for Markov decision problems with the total reward criterion ⋮ Action-dependent stopping times and Markov decision process with unbounded rewards