Non-randomized strategies in stochastic decision processes

DOI10.1007/BF02283603zbMath0717.90092MaRDI QIDQ2638965

Eugene A. Feinberg

Publication date: 1991

Published in: Annals of Operations Research (Search for Journal in Brave)

zbMATH Keywords

discrete-time infinite-horizon stochastic decision processesnon- randomized strategies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items

Finite state Markov decision models with average reward criteria

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The existence of good Markov strategies for decision processes with general payoffs
• Stochastic optimal control. The discrete time case
• The optimal reward operator in dynamic programming
• Stationary Policies in Dynamic Programming Models Under Compactness Assumptions
• Controlled random sequences and Markov chains
• Controlled Markov Processes with Arbitrary Numerical Criteria
• Sufficient Classes of Strategies in Discrete Dynamic Programming I: Decomposition of Randomized Strategies and Embedded Models
• Markov Strategies in Dynamic Programming
• Non-Randomized Markov and Semi-Markov Strategies in Dynamic Programming
• On the Existence of Good Markov Strategies
• Negative Dynamic Programming