The optimal reward operator in dynamic programming

DOI10.1214/AOP/1176996558MaRDI QIDQ1222389zbMATH OpenOpenAlexFDO

Authors David Freedman, Michael Orkin, D. Blackwell

Publication date 1974

Published in The Annals of Probability (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1214/aop/1176996558

Mathematics Subject Classification ID

Special processes (60K99) Classes of sets (Borel fields, (sigma)-rings, etc.), measurable sets, Suslin sets, analytic sets (28A05) Hamilton-Jacobi theories (49L99) Mathematical programming (90C99)

Cited in

(27)

• Some results on analytic spaces and semi-analytic functions with regard to gambling theory
• Multi-factor dynamic investment under uncertainty
• On the complexity of linear quadratic control
• Measurable selection theorems for optimization problems
• Measurable, nonleavable gambling problems
• A mixed value and policy iteration method for stochastic control with universally measurable policies
• Bounded variation of \(\{V_ n\}\) and its limit
• How to stay in a set or Koenig's lemma for random paths
• Big vee: the story of a function, an algorithm, and three mathematical worlds
• Stochastic games with metric state space
• Finitely additive dynamic programming
• Estimates for finite-stage dynamic programs
• Leavable Gambling Problems with Unbounded Utilities
• Risk, uncertainty, and complexity
• Conditions for characterizing the structure of optimal strategies in infinite-horizon dynamic programs
• On convergence of value iteration for a class of total cost Markov decision processes
• Countably additive gambling and optimal stopping
• The transformation method for continuous-time Markov decision processes
• On the optimality of (s, S)-strategies in a minimax inventory model with average cost criterion
• Non-randomized strategies in stochastic decision processes
• Average cost optimality inequality for Markov decision processes with Borel spaces and universally measurable policies
• On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies
• Semicontinuous nonstationary stochastic games. II
• Stationary policies and Markov policies in Borel dynamic programming
• EQUILIBRIUM STRATEGIES IN STOCHASTIC GAMES WITH ADDITIVE COST AND TRANSITION STRUCTURE
• On measurable minimax selectors
• On a theorem of Wald and Wolfowitz on randomization in statistics

This page was built for publication: The optimal reward operator in dynamic programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1222389)