Non-Randomized Markov and Semi-Markov Strategies in Dynamic Programming

DOI10.1137/1127010zbMath0499.60093OpenAlexW1993561151MaRDI QIDQ3965372

Eugene A. Feinberg

Publication date: 1982

Published in: Theory of Probability & Its Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/1127010

zbMATH Keywords

Markov decision modelsemi-Markov policy

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Dynamic programming (90C39) Markov renewal processes, semi-Markov processes (60K15)

Related Items (13)

Utility, probabilistic constraints, mean and variance of discounted rewards in Markov decision processes ⋮ The existence of good Markov strategies for decision processes with general payoffs ⋮ Non-randomized strategies in stochastic decision processes ⋮ On an extremal property of Markov chains and sufficiency of Markov strategies in Markov decision processes with the Dubins-Savage criterion ⋮ Finding Optimal Survey Policies via Adaptive Markov Decision Processes ⋮ Geometry of information structures, strategic measures and associated stochastic control topologies ⋮ Convex Analysis in Decentralized Stochastic Control, Strategic Measures, and Optimal Solutions ⋮ A Universal Dynamic Program and Refined Existence Results for Decentralized Stochastic Control ⋮ Optimal control problem regularization for the Markov process with finite number of states and constraints ⋮ Sufficiency of Deterministic Policies for Atomless Discounted and Uniformly Absorbing MDPs with Multiple Criteria ⋮ On a generalization of the Dvoretzky-Wald-Wolfowitz theorem with an application to a robust optimization problem ⋮ Finite-stage reward functions having the Markov adequacy property ⋮ Multiple objective nonatomic Markov decision processes with total reward criteria

This page was built for publication: Non-Randomized Markov and Semi-Markov Strategies in Dynamic Programming