Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards

DOI10.1016/0022-247X(82)90271-2zbMath0533.90094MaRDI QIDQ790055

Douglas J. White

Publication date: 1982

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

zbMATH Keywords

approximation errors; Markov decision problems; 262.90064; 309.90017; 354.90087; 428.90082; 431.90080; denumerable states; unbounded reward vector

Mathematics Subject Classification ID

90C40: Markov and semi-Markov decision processes

Related Items

Asymptotic properties of constrained Markov Decision Processes, Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards, Approximating Markov decision processes using expected state transitions, Finite-state approximations for denumerable multidimensional state discounted Markov decision processes, Finite-state approximations for denumerable state discounted Markov decision processes, A priori bounds for approximations of Markov programs, Finite state approximation for denumerable-state infinite horizon contracted Markov decision processes: The policy space method, A stability result for linear Markovian stochastic optimization problems

Cites Work

• Unnamed Item
• Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards
• Finite-state approximations for denumerable-state infinite-horizon discounted Markov decision processes
• Finite state approximation for denumerable-state infinite horizon contracted Markov decision processes: The policy space method
• Markov programming by successive approximations with respect to weighted supremum norms
• On Dynamic Programming with Unbounded Rewards
• Note—A Note on Dynamic Programming with Unbounded Rewards
• Contraction Mappings in the Theory Underlying Dynamic Programming
• Discrete Dynamic Programming with Unbounded Rewards