Memoryless Strategies in Finite-Stage Dynamic Programming

DOI10.1214/aoms/1177703586zbMath0127.36406OpenAlexW2019669033MaRDI QIDQ5334726

David Blackwell

Publication date: 1964

Published in: The Annals of Mathematical Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aoms/1177703586

zbMATH Keywords

operations research

Related Items

Markovian equilibrium in a class of stochastic games: Existence theorems for discounted and undiscounted models ⋮ A Mixed Value and Policy Iteration Method for Stochastic Control with Universally Measurable Policies ⋮ Geometry of information structures, strategic measures and associated stochastic control topologies ⋮ Convex Analysis in Decentralized Stochastic Control, Strategic Measures, and Optimal Solutions ⋮ An algorithmic approach to identify irrelevant information in sequential teams ⋮ A Universal Dynamic Program and Refined Existence Results for Decentralized Stochastic Control ⋮ Markov-achievable payoffs for finite-horizon decision models. ⋮ The topology of information on the space of probability measures over Polish spaces ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Weak Feller property of non-linear filters ⋮ Convex analytic method revisited: further optimality results and performance of deterministic policies in average cost stochastic control ⋮ On the Existence of Optimal Policies for a Class of Static and Sequential Dynamic Teams ⋮ Optimal Policies for Convex Symmetric Stochastic Dynamic Teams and their Mean-Field Limit