Finite state approximation for denumerable-state infinite horizon contracted Markov decision processes: The policy space method

DOI10.1016/0022-247X(79)90244-0zbMath0431.90080MaRDI QIDQ1138486

Douglas J. White

Publication date: 1979

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

zbMATH Keywords

convergence analysiscountable state spacefinite state approximationsbounded set of rewardsfinite state computational schemeinfinite horizon contracted Markov decision processespolicy space methodsteady state Markov decision process

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47)

Related Items (4)

Isotone optimal policies for structured Markov decision processes ⋮ Discrete type shock semi-markov decision processes with borel state space ⋮ Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards ⋮ Finite state approximation algorithms for average cost denumerable state Markov decision processes

Cites Work

• Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards
• Finite-state approximations to denumerable-state dynamic programs

This page was built for publication: Finite state approximation for denumerable-state infinite horizon contracted Markov decision processes: The policy space method