On the Optimality of Structured Policies in Countable Stage Decision Processes. II: Positive and Negative Problems

DOI10.1137/0132038MaRDI QIDQ4132298zbMATH OpenOpenAlexWikidataFDO

Authors David M. Kreps, Evan L. Porteus

Publication date 1977

Published in SIAM Journal on Applied Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/0132038

Mathematics Subject Classification ID

Markov processes (60J99) Decision theory for games (91A35) Hamilton-Jacobi theories (49L99) Stochastic games, stochastic differential games (91A15)

Cited in

(4)

• On convergence of value iteration for a class of total cost Markov decision processes
• A mixed value and policy iteration method for stochastic control with universally measurable policies
• Conditions for characterizing the structure of optimal strategies in infinite-horizon dynamic programs
• On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes

This page was built for publication: On the Optimality of Structured Policies in Countable Stage Decision Processes. II: Positive and Negative Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4132298)