Discounting, Ergodicity and Convergence for Markov Decision Processes

DOI10.1287/MNSC.23.8.890MaRDI QIDQ4132287zbMATH OpenOpenAlexFDO

Authors Thomas E. Morton, William E. Wecker

Publication date 1977

Published in Management Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/mnsc.23.8.890

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cited in

(13)

• A survey of algorithmic methods for partially observed Markov decision processes
• Computation techniques for large scale undiscounted markov decision processes
• Improved iterative computation of the expected discounted return in Markov and semi-Markov chains
• Serial and parallel value iteration algorithms for discounted Markov decision processes
• The infinite horizon non-stationary stochastic inventory problem: Near myopic policies and weak ergodicity
• Contraction mappings underlying undiscounted Markov decision problems
• Decision and forecast horizons in a stochastic environment: A survey
• The rate of convergence for backwards products of a convergent sequence of finite Markov matrices
• Solving linear systems by methods based on a probabilistic interpretation
• The method of value oriented successive approximations for the average reward Markov decision process
• Action-dependent stopping times and Markov decision process with unbounded rewards
• Sensitivity analysis in discrete dynamic programming
• Periodic review stochastic inventory problem with forecast updates: Worst-case bounds for the myopic solution

This page was built for publication: Discounting, Ergodicity and Convergence for Markov Decision Processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4132287)