The optimal reward operator in dynamic programming

DOI10.1214/aop/1176996558zbMath0318.49021OpenAlexW1975828588MaRDI QIDQ1222389

David Freedman, Michael Orkin, David 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

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

Related Items (27)

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

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