Discounting, Ergodicity and Convergence for Markov Decision Processes

DOI10.1287/mnsc.23.8.890zbMath0358.90073MaRDI QIDQ4132287

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

90C40: Markov and semi-Markov decision processes

Related Items

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