Uniform Turnpike Theorems for Finite Markov Decision Processes
Published Online:14 Sep 2018https://doi.org/10.1287/moor.2017.0912
References
- (2014) The value iteration algorithm is not strongly polynomial for discounted dynamic programming. Oper. Res. Lett. 42(2):130–131.Crossref, Google Scholar
- (1976) Methods of Real Analysis, 2nd ed. (John Wiley & Sons, Hoboken, NJ).Google Scholar
- (1985) Sensitivity-analysis in discounted Markovian decision problems. OR Spektrum 7(3):143–151.Crossref, Google Scholar
- (2009) Markov decision processes. Lecture notes, University of Leiden, Leiden, Netherlands. http://www.math.leidenuniv.nl/~kallenberg/Lecture-notes-MDP.pdf.Google Scholar
- (2011) An overview of turnpike theory: Towards the discounted deterministic case. Kusuoka S, Maruyama T, eds. Advances on Mathematical Economics, Vol. 14 (Springer, Tokyo), 39–67.Crossref, Google Scholar
- (1994) Markov Decision Processes: Discrete Stochastic Dynamic Programming, Wiley Series in Probability and Mathematical Statistics (John Wiley & Sons, New York).Crossref, Google Scholar
- (1999) Stochastic Dynamic Programming and the Control of Queueing Systems, Wiley Series in Probability and Statistics (John Wiley & Sons, New York).Google Scholar
- (1968) Turnpike planning horizons for a Markovian decision model. Management Sci. 14(5):292–300.Link, Google Scholar
- (1966) Optimum policy regions for Markov processes with discounting. Oper. Res. 14(4):658–669.Link, Google Scholar
- (1990) Solving H-horizon, stationary Markov decision problems in time proportional to log(H). Oper. Res. Lett. 9(5):287–297.Crossref, Google Scholar
- (2011) The simplex and policy-iteration methods are strongly polynomial for the Markov decision problem with a fixed discount rate. Math. Oper. Res. 36(4):593–603.Link, Google Scholar
- (2014) Stability of the Turnpike Phenomenon in Discrete-Time Optimal Control Problems (Springer International Publishing AG, Cham, Switzerland).Crossref, Google Scholar

