Finite-state approximations for denumerable state discounted Markov decision processes

DOI10.1007/BF01442225zbMath0606.90132MaRDI QIDQ1085078

Rolando Cavazos-Cadena

Publication date: 1986

Published in: Applied Mathematics and Optimization (Search for Journal in Brave)

zbMATH Keywords

rate of convergencesuccessive approximationsasymptotic discount optimalitydenumerable state discounted Markov decision processesfinite-state approximationsgeneral conditions of convergenceunbounded rewards

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (10)

Constrained discounted stochastic games ⋮ Nonzero-sum constrained discrete-time Markov games: the case of unbounded costs ⋮ Density estimation and adaptive control of Markov processes: Average and discounted criteria ⋮ Decentralized stochastic control ⋮ An optimal control approach to day-to-day congestion pricing for stochastic transportation networks ⋮ Asymptotic optimality and rates of convergence of quantized stationary policies in continuous-time Markov decision processes ⋮ Exact finite approximations of average-cost countable Markov decision processes ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Approximations of Countably Infinite Linear Programs over Bounded Measure Spaces

Cites Work

• Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards
• Adaptive control of discounted Markov decision chains
• Finite-state approximations for denumerable-state infinite-horizon discounted Markov decision processes
• Markov programming by successive approximations with respect to weighted supremum norms
• Finite-state approximations to denumerable-state dynamic programs
• On Dynamic Programming with Unbounded Rewards
• Discrete Dynamic Programming with Unbounded Rewards

This page was built for publication: Finite-state approximations for denumerable state discounted Markov decision processes