The existence of good Markov strategies for decision processes with general payoffs

DOI10.1016/0304-4149(87)90028-7zbMath0627.90094OpenAlexW1997109950MaRDI QIDQ1092823

Victor C. Pestien, Theodore P. Hill

Publication date: 1987

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL: https://digitalcommons.calpoly.edu/cgi/viewcontent.cgi?article=1021&context=rgp_rsr

zbMATH Keywords

countable-state stochastic dynamic programminggeneral class of reward structuresrandomized Markov strategies

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items

Strategy Complexity of Point Payoff, Mean Payoff and Total Payoff Objectives in Countable MDPs, 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, Finite-stage stochastic decision processes with recursive reward structure I: optimality equations and deterministic strategies, Markov-achievable payoffs for finite-horizon decision models., Finite-stage reward functions having the Markov adequacy property, Utility Functions Which Ensure the Adequacy of Stationary Strategies, Optimal Markov strategies, Finite state Markov decision models with average reward criteria

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On maximizing the average time at a goal
• Stationary Policies in Dynamic Programming Models Under Compactness Assumptions
• Multiplicative Markov Decision Chains
• Controlled Markov Processes with Arbitrary Numerical Criteria
• Gambling Problems with a Limit Inferior Payoff
• Markov Strategies in Dynamic Programming
• Non-Randomized Markov and Semi-Markov Strategies in Dynamic Programming
• Decision Problems with Expected Utility Critera, I: Upper and Lower Convergent Utility
• Decision Problems with Expected Utility Criteria, II: Stationarity
• On the Existence of Good Markov Strategies
• Discounted Dynamic Programming
• A Note on Memoryless Rules for Controlling Sequential Control Processes
• Negative Dynamic Programming
• On the Existence of Stationary Optimal Strategies