The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Markov decision processes: Discrete stochastic dynamic programming
Abstract
From the Publisher: The past decade has seen considerable theoretical and applied research on Markov decision processes, as well as the growing use of these models in ecology, economics, communications engineering, and other fields where outcomes are uncertain and sequential decision-making processes are needed. A timely response to this increased activity, Martin L. Puterman's new work provides a uniquely up-to-date, unified, and rigorous treatment of the theoretical, computational, and applied research on Markov decision process models. It discusses all major research directions in the field, highlights many significant applications of Markov decision processes models, and explores numerous important topics that have previously been neglected or given cursory coverage in the literature. Markov Decision Processes focuses primarily on infinite horizon discrete time models and models with discrete time spaces while also examining models with arbitrary state spaces, finite horizon models, and continuous-time discrete state models. The book is organized around optimality criteria, using a common framework centered on the optimality (Bellman) equation for presenting results. The results are presented in a theorem-proof format and elaborated on through both discussion and examples, including results that are not available in any other book. A two-state Markov decision process model, presented in Chapter 3, is analyzed repeatedly throughout the book and demonstrates many results an…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Bellman, R. E. (2010) · doi:10.1515/9781400835386 · Cited by 14,588
Rudin, W. (1973) · Cited by 13,740
Introduction to Stochastic Dynamic Programming.
Berry, D. A., & Ross, S. M. (1986) · Journal of the American Statistical Association · doi:10.2307/2289262 · Cited by 1,130
White, C. C., & White, D. J. (1989) · European Journal of Operational Research · doi:10.1016/0377-2217(89)90348-2 · Cited by 422
Dynamic programming: Models and applications
Denardo, E. V. (1982) · CERN Document Server (European Organization for Nuclear Research) · Cited by 411
Finding Optimal (s, S) Policies Is About As Simple As Evaluating a Single Policy
Zheng, Y., & Federgruen, A. (1991) · Operations Research · doi:10.1287/opre.39.4.654 · Cited by 317
Optimization over Time. Dynamic Programming and Stochastic Control. Volume 1
Thomas, L. C., & Whittle, P. (1983) · Journal of the Operational Research Society · doi:10.1057/jors.1983.56 · Cited by 162
Dynamic Programming and Its Application
Puterman, M. L. (1979) · Academic Press, Inc. eBooks · Cited by 57
Self-citationOn Homogeneous Markov Models with Continuous Time and Finite or Countable State Space
Yushkevic, A. A., & Fainberg, E. A. (1979) · Theory of Probability and Its Applications · doi:10.1137/1124014 · Cited by 34
Finite Dynamic Programming: An Approach to Finite Markov Decision Processes
White, D. J. (1978) · Andalas University Repository (Andalas University) · Cited by 24
Handbooks in operations research and management science volume 2: Stochastic models
Pintelon, L. M. (1991) · European Journal of Operational Research · doi:10.1016/0377-2217(91)90047-y · Cited by 13
Markov: A methodology for the solution of infinite time horizon markov decision processes
Williams, B. K. (1988) · Applied Stochastic Models and Data Analysis · doi:10.1002/asm.3150040405 · Cited by 11
Flagged first, then by citations
Cited by
Sorted by citations
Reinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972
Machine learning: Algorithms, real-world applications and research directions
Sarker, I. H. (2021) · SN Computer Science · doi:10.1007/s42979-021-00592-x · Cited by 5,583
“The problem to be solved in reinforcement learning (RL) is defined as a Markov Decision Process (MDP) [86], i.”
InfluentialPlanning and acting in partially observable stochastic domains
Kaelbling, L. P., Littman, M. L., & Cassandra, A. R. (1998) · Artificial Intelligence · doi:10.1016/s0004-3702(98)00023-x · Cited by 4,149
Bayesian Networks and Decision Graphs
Jensen, F. V., & Nielsen, T. D. (2007) · Information science and statistics · doi:10.1007/978-0-387-68282-2 · Cited by 4,157
Reinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160
Metadata
- Authors
- Hazeghi, K., & Puterman, M. L.
- ORCID
- Puterman, Martin L.
- Venue
- Journal of the American Statistical Association
- Publisher
- JSTOR
- Published
- 1995-03
- Volume
- 90
- Issue
- 429
- Pages
- 392
- ISSN
- 0162-1459 (ISSN-L)
- OpenAlex
- W2119567691
- Cited by
- 8,037
- References
- 12
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 86 · 2023: 145 · 2022: 233 · 2021: 616 · 2020: 674 · 2019: 595 · 2018: 480 · 2017: 459 · 2016: 450 · 2015: 507 · 2014: 451 · 2013: 420 · 2012: 392
- Type
- book review
- Language
- en
- Open access
- closed
- Locations
- Journal of the American Statistical Association (publishedVersion)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Adaptive Dynamic Programming Control
- Physical Sciences › Mathematics › Statistics and Probability › Probability and Statistical Research
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- Markov decision process, stochastic dynamic programming, discrete-time models, infinite horizon model, finite horizon model, Bellman equation, optimality criteria, average reward criterion, constrained models, sequential decision making under uncertainty
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
