Universally Measurable Policies in Dynamic Programming
DOI10.1287/MOOR.4.1.15zbMATH Open0412.90071OpenAlexW2018546408MaRDI QIDQ4199855FDOQ4199855
Steven Shreve, Dimitri P. Bertsekas
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
dynamic programmingconvergence analysisdiscrete timeMarkov decision processesanalytic setsBorel spacesprogramming in abstract spacesuniversally measurable policiesexistence of epsilon-optimal policies
Dynamic programming (90C39) 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)
Cited In (16)
- How to stay in a set or Koenig's lemma for random paths
- Discrete type shock semi-markov decision processes with borel state space
- On Convergence of Value Iteration for a Class of Total Cost Markov Decision Processes
- Mixed Markov decision processes in a semi-Markov environment with discounted criterion
- Continuous time shock markov decision processes with discounted criterion
- On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs
- Stackelberg equilibrium in a dynamic stimulation model with complete information
- A Mixed Value and Policy Iteration Method for Stochastic Control with Universally Measurable Policies
- Average Cost Optimality Inequality for Markov Decision Processes with Borel Spaces and Universally Measurable Policies
- Conditions for characterizing the structure of optimal strategies in infinite-horizon dynamic programs
- A limited order capacity stochastic inventory model with a fixed cost for order: The discounted case
- Discounted semi-markov decision process in a semi-markov environment
- On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies
- Quantitative model-checking of controlled discrete-time Markov processes
- On measurable minimax selectors
- Continuous time markov decision processes with nonuniformly bounded transition rate: expected total rewards
This page was built for publication: Universally Measurable Policies in Dynamic Programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4199855)
