The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Robust Control of Markov Decision Processes with Uncertain Transition Matrices
Abstract
Optimal solutions to Markov decision problems may be very sensitive with respect to the state transition probabilities. In many practical problems, the estimation of these probabilities is far from accurate. Hence, estimation errors are limiting factors in applying Markov decision processes to real-world problems. We consider a robust control problem for a finite-state, finite-action Markov decision process, where uncertainty on the transition matrices is described in terms of possibly nonconvex sets. We show that perfect duality holds for this problem, and that as a consequence, it can be solved with a variant of the classical dynamic programming algorithm, the “robust dynamic programming” algorithm. We show that a particular choice of the uncertainty sets, involving likelihood regions or entropy bounds, leads to both a statistically accurate representation of uncertainty, and a complexity of the robust recursion that is almost the same as that of the classical recursion. Hence, robustness can be added at practically no extra computing cost. We derive similar results for other uncertainty sets, including one with a finite number of possible values for the transition matrices. We describe in a practical path planning example the benefits of using a robust strategy instead of the classical optimal strategy; even if the uncertainty level is only crudely guessed, the robust strategy yields a much better worst-case expected travel time.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
Markov decision processes: Discrete stochastic dynamic programming
Hazeghi, K., & Puterman, M. L. (1995) · Journal of the American Statistical Association · doi:10.2307/2291177 · Cited by 8,037
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Puterman, M. L. (1994) · Wiley Series in Probability and Statistics · doi:10.1002/9780470316887 · Cited by 6,024
Ziegel, E. R., Lehmann, E. L., & Casella, G. (1999) · Technometrics · doi:10.2307/1270597 · Cited by 4,203
(2012) · Encyclopedia of the Sciences of Learning · doi:10.1007/978-1-4419-1428-6_5086 · Cited by 3,515
An Introduction to Signal Detection and Estimation
Poor, H. V. (1988) · Springer Texts in Electrical Engineering · doi:10.1007/978-1-4757-3863-6 · Cited by 3,149
Testing Statistical Hypotheses
Lehmann, E. L. (1986) · Springer Texts in Statistics · doi:10.1007/978-1-4757-1923-9 · Cited by 1,873
(1998) · Springer Texts in Statistics · doi:10.1007/b98854 · Cited by 1,719
Neuro-Dynamic Programming: NDP
Bertsekas, D. P. (2001) · Encyclopedia of Optimization · doi:10.1007/0-306-48332-7_333 · Cited by 1,466
Testing Statistical Hypothesis.
Crouse, C. F., & Lehmann, E. L. (1960) · Biometrika · doi:10.2307/2332982 · Cited by 745
Iyengar, G. N. (2005) · Mathematics of Operations Research · doi:10.1287/moor.1040.0129 · Cited by 566
Handbook of Markov Decision Processes
Feinberg, E. A., & Shwartz, A. (2002) · International series in management science/operations research/International series in operations research & management science · doi:10.1007/978-1-4615-0805-2 · Cited by 551
Handbook of Markov decision processes : methods and applications
Feinberg, E. A., & Shwartz, A. (2002) · Cited by 313
Bounded-parameter Markov decision processes
Givan, R., Leach, S., & Dean, T. (2000) · Artificial Intelligence · doi:10.1016/s0004-3702(00)00047-3 · Cited by 308
Markovian Decision Processes with Uncertain Transition Probabilities
Satia, J. K., & Lave, R. E. (1973) · Operations Research · doi:10.1287/opre.21.3.728 · Cited by 224
Markov Decision Processes with Imprecise Transition Probabilities
White, C. C., & Eldeib, H. K. (1994) · Operations Research · doi:10.1287/opre.42.4.739 · Cited by 168
Cited by
(2015) · Journal of Machine Learning Research · Cited by 1,119
Optimization for Machine Learning
(2011) · The MIT Press eBooks · doi:10.7551/mitpress/8996.001.0001 · Cited by 875
Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning
Brunke, L., Greeff, M., Hall, A. W., Yuan, Z., Zhou, S., Panerati, J., & Schoellig, A. P. (2022) · Annual Review of Control, Robotics, and Autonomous Systems · doi:10.1146/annurev-control-042920-020211 · Cited by 769
Chen, X., Qu, G., Tang, Y., Low, S., & Li, N. (2022) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2022.3154718 · Cited by 415
Quantifying Distributional Model Risk via Optimal Transport
Blanchet, J., & Murthy, K. (2019) · Mathematics of Operations Research · doi:10.1287/moor.2018.0936 · Cited by 350
Metadata
- Authors
- Nilim, A., & El Ghaoui, L.
- Venue
- Operations Research
- Published
- 2005-10
- Volume
- 53
- Issue
- 5
- Pages
- 780-798
- ISSN
- 0030-364X (ISSN-L)
- 1526-5463
- OpenAlex
- W1965878388
- Cited by
- 694
- References
- 16
- FWCI
- 16.74
- Type
- journal article
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.