Universally Measurable Policies in Dynamic Programming

DOI10.1287/moor.4.1.15zbMath0412.90071OpenAlexW2018546408MaRDI QIDQ4199855

Dimitri P. Bertsekas, Steven E. Shreve

Publication date: 1979

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

Full work available at URL: https://doi.org/10.1287/moor.4.1.15

zbMATH Keywords

convergence analysisdynamic programmingMarkov decision processesanalytic setsdiscrete timeBorel spacesprogramming in abstract spacesuniversally measurable policiesexistence of epsilon-optimal policies

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Classes of sets (Borel fields, (sigma)-rings, etc.), measurable sets, Suslin sets, analytic sets (28A05) Discrete-time control/observation systems (93C55) Dynamic programming (90C39)

Related Items (16)

A Mixed Value and Policy Iteration Method for Stochastic Control with Universally Measurable Policies ⋮ Continuous time shock markov decision processes with discounted criterion ⋮ Conditions for characterizing the structure of optimal strategies in infinite-horizon dynamic programs ⋮ Discounted semi-markov decision process in a semi-markov environment ⋮ 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 ⋮ Quantitative model-checking of controlled discrete-time Markov processes ⋮ A limited order capacity stochastic inventory model with a fixed cost for order: The discounted case ⋮ Discrete type shock semi-markov decision processes with borel state space ⋮ Continuous time markov decision processes with nonuniformly bounded transition rate: expected total rewards ⋮ On measurable minimax selectors ⋮ Stackelberg equilibrium in a dynamic stimulation model with complete information ⋮ On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs ⋮ Mixed Markov decision processes in a semi-Markov environment with discounted criterion ⋮ 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

This page was built for publication: Universally Measurable Policies in Dynamic Programming