Finitely additive dynamic programming

DOI10.1287/MOOR.2015.0717MaRDI QIDQ2800365zbMATH OpenOpenAlexFDO

Authors William D. Sudderth

Publication date 15 April 2016

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/moor.2015.0717

zbMATH Keywords

dynamic programmingMarkov decision processesfinitely additive probability

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20) Set functions and measures on spaces with additional structure (28C99)

Recommendations

• scientific article; zbMATH DE number 4097158
• scientific article; zbMATH DE number 4097157
• Dynamic programming for controlled Markov families: abstractly and over martingale measures
• Some applications of the theory of dynamic programming -- a review
• On temporal aggregators and dynamic programming

Cites work

• scientific article; zbMATH DE number 3816010 (Why is no real title available?)
• scientific article; zbMATH DE number 1786118 (Why is no real title available?)
• scientific article; zbMATH DE number 3216771 (Why is no real title available?)
• scientific article; zbMATH DE number 3301983 (Why is no real title available?)
• An example in which stationary strategies are not adequate
• Big vee: the story of a function, an algorithm, and three mathematical worlds
• Discounted Dynamic Programming
• Discrete Dynamic Programming
• Finitely additive and measurable stochastic games
• Finitely additive stochastic games with Borel measurable payoffs
• Measurable Gambling Houses
• Measurable, nonleavable gambling problems
• Negative Dynamic Programming
• On optimal policies and martingales in dynamic programming
• On the Existence of Stationary Optimal Strategies
• Persistently optimal plans for nonstationary dynamic programming: The topology of weak convergence case
• Persistently optimal policies in stochastic dynamic programming with generalized discounting
• Persistently ϵ-Optimal Strategies
• Some finitely additive probability
• Stationary Plans need not be Uniformly Adequate for Leavable, Borel Gambling Problems
• Subgame-perfect equilibria of finite- and infinite-horizon games
• The Optimal Reward Operator in Negative Dynamic Programming
• The optimal reward operator in dynamic programming
• Two characterizations of optimality in dynamic programming
• Uniform value in dynamic programming

Cited in

(11)

• scientific article; zbMATH DE number 4024378 (Why is no real title available?)
• scientific article; zbMATH DE number 3889838 (Why is no real title available?)
• Finitely additive behavioral strategies: when do they induce an unambiguous expected payoff?
• scientific article; zbMATH DE number 4097157 (Why is no real title available?)
• scientific article; zbMATH DE number 4097158 (Why is no real title available?)
• On the equivalence of mixed and behavior strategies in finitely additive decision problems
• Optimal Markov strategies
• Upper and lower conditional probabilities induced by a multivalued mapping
• Envelopes of conditional probabilities extending a strategy and a prior probability
• scientific article; zbMATH DE number 4170669 (Why is no real title available?)
• Zero-sum games with charges

This page was built for publication: Finitely additive dynamic programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2800365)