The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Reinforcement Learning for Partially Observable Dynamic Processes: Adaptive Dynamic Programming Using Measured Output Data
Abstract
Approximate dynamic programming (ADP) is a class of reinforcement learning methods that have shown their importance in a variety of applications, including feedback control of dynamical systems. ADP generally requires full information about the system internal states, which is usually not available in practical situations. In this paper, we show how to implement ADP methods using only measured input/output data from the system. Linear dynamical systems with deterministic behavior are considered herein, which are systems of great interest in the control system community. In control system theory, these types of methods are referred to as output feedback (OPFB). The stochastic equivalent of the systems dealt with in this paper is a class of partially observable Markov decision processes. We develop both policy iteration and value iteration algorithms that converge to an optimal controller that requires only OPFB. It is shown that, similar to Q -learning, the new methods have the important advantage that knowledge of the system dynamics is not needed for the implementation of these learning algorithms or for the OPFB control. Only the order of the system, as well as an upper bound on its "observability index," must be known. The learned OPFB controller is in the form of a polynomial autoregressive moving-average controller that has equivalent performance with the optimal state variable feedback gain.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Optimal feedback control systems have been applied to basic sensorimotor control [97] and to reinforcement learning models [98].”
From Health behavior models in the age of mobile interventions: are our theories up to the task? (2011) · cites this paper as [98]
Citations
Cites
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 25,268
A neural substrate of prediction and reward
Schultz, W., Dayan, P., & Montague, P. R. (1997) · Science · doi:10.1126/science.275.5306.1593 · Cited by 9,388
Watkins, C. (1989) · OpenGrey (Institut de l'Information Scientifique et Technique) · doi:10.17863/cam.132164 · Cited by 5,674
(2012) · Springer eBooks · doi:10.1007/978-1-4419-1428-6_5086 · Cited by 3,601
Lewis, F. L. (1986) · Cited by 2,957
Self-citationBeyond regression : new fools for prediction and analysis in the behavioral sciences
Werbos, P. J. (1974) · Medical Entomology and Zoology · Cited by 2,739
Approximate Dynamic Programming
Powell, W. B. (2011) · Wiley series in probability and statistics · doi:10.1002/9781118029176 · Cited by 2,359
Kronecker products and matrix calculus in system theory
Brewer, J. (1978) · IEEE Transactions on Circuits and Systems · doi:10.1109/tcs.1978.1084534 · Cited by 1,920
Online actor–critic algorithm to solve the continuous-time infinite horizon optimal control problem
Vamvoudakis, K. G., & Lewis, F. L. (2010) · Automatica · doi:10.1016/j.automatica.2010.02.018 · Cited by 1,722
Self-citationReinforcement learning and adaptive dynamic programming for feedback control
Lewis, F. L., & Vrabie, D. (2009) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2009.933854 · Cited by 1,591
Self-citationApproximate Dynamic Programming
Powell, W. B. (2007) · Wiley series in probability and statistics · doi:10.1002/9780470182963 · Cited by 1,582
Lancaster, P., & Rodman, L. (1995) · doi:10.1093/oso/9780198537953.001.0001 · Cited by 1,218
Prokhorov, D. V., & Wunsch, D. C. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.623201 · Cited by 1,189
Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence Proof
Al-Tamimi, A., Lewis, F. L., & Abu-Khalaf, M. (2008) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2008.926614 · Cited by 1,073
Self-citationIterative feedback tuning: theory and applications
Hjalmarsson, H., GEVERS, M. R., Gunnarsson, S., & Lequin, O. (1998) · IEEE Control Systems · doi:10.1109/37.710876 · Cited by 995
Reinforcement Learning in Continuous Time and Space
Doya, K. (2000) · Neural Computation · doi:10.1162/089976600300015961 · Cited by 995
(2010) · Springer eBooks · doi:10.1007/978-0-387-30164-8_588 · Cited by 978
Ioannou, P., & Fi̇dan, B. (2006) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9780898718652 · Cited by 977
Approximate dynamic programming for real-time control and neural modeling
Werbos, P. J. (1992) · Medical Entomology and Zoology · Cited by 971
Adaptive Dynamic Programming: An Introduction
Wang, F., Zhang, H., & Liu, D. (2009) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2009.932261 · Cited by 901
Handbook of Learning and Approximate Dynamic Programming
Si, J., Barto, A. G., Powell, W. B., & Wunsch, D. C. (2004) · Institute of Electrical and Electronics Engineers eBooks · doi:10.1109/9780470544785 · Cited by 863
Stabilization of Nonlinear Uncertain Systems
Krstić, M., Modestino, J. W., Deng, H., Fettweis, A., Massey, J. L., Thoma, M., Sontag, E. D., & Dickinson, B. (1998) · Cited by 626
The unfalsified control concept and learning
Safonov, M. G., & Tsao, T. (1997) · IEEE Transactions on Automatic Control · doi:10.1109/9.587340 · Cited by 602
Widrow, B. C., & Bilello, M. (2002) · The proceedings of the IEEE Conference on Control Applications/The proceedings of the ... IEEE Conference on Control Applications · doi:10.1109/isic.1993.397732 · Cited by 592
Schultz, W. (2004) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2004.03.017 · Cited by 517
Adaptive linear quadratic control using policy iteration
Bradtke, S. J., Ydstie, B. E., & Barto, A. G. (2005) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.1994.735224 · Cited by 414
Rogers, S. C. (1997) · Control Engineering Practice · doi:10.1016/s0967-0661(97)89242-8 · Cited by 328
Hewer, G. (1971) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1971.1099755 · Cited by 326
Neural networks for control and system identification
Werbos, P. J. (2003) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.1989.70114 · Cited by 323
Stochastic Learning and Optimization
Cao, X. (2007) · Springer eBooks · doi:10.1007/978-0-387-69082-7 · Cited by 243
Model-free control of nonlinear stochastic systems with discrete-time measurements
Spall, J. C., & Cristion, J. A. (1998) · IEEE Transactions on Automatic Control · doi:10.1109/9.718605 · Cited by 241
Lewis, F. L., Xie, L., & Popa, D. O. (2017) · CRC Press eBooks · doi:10.1201/9781315221656 · Cited by 222
Self-citationVirtual reference feedback tuning for two degree of freedom controllers
Lecchini, A., Campi, M. C., & Savaresi, S. M. (2002) · International Journal of Adaptive Control and Signal Processing · doi:10.1002/acs.711 · Cited by 158
Q-learning and Pontryagin's Minimum Principle
Mehta, P. G., & Meyn, S. (2009) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2009.5399753 · Cited by 127
Optimal design of adaptive tracking controllers for non-linear systems
Li, Z., & Krstić, M. (1997) · Automatica · doi:10.1016/s0005-1098(97)00072-1 · Cited by 110
Neural mechanisms of learning and control
Doya, K., Kimura, H., & Kawato, M. (2001) · IEEE Control Systems · doi:10.1109/37.939943 · Cited by 103
Aangenent, W., Kostic, D., de Jager, B., van de Molengraft, R., & Steinbuch, M. (2005) · Proceedings of the 2005, American Control Conference, 2005. · doi:10.1109/acc.2005.1470171 · Cited by 70
Adaptive optimal controllers based on Generalized Policy Iteration in a continuous-time framework
Vrabie, D., Vamvoudakis, K. G., & Lewis, F. L. (2009) · Mediterranean Conference on Control and Automation (MED) · doi:10.1109/med.2009.5164743 · Cited by 62
Self-citationOnline actor critic algorithm to solve the continuous-time infinite horizon optimal control problem
Vamvoudakis, K. G., & Lewis, F. L. (2009) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2009.5178586 · Cited by 57
Self-citationLewis, F. L., Liu, D., & Lendaris, G. G. (2008) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2008.925890 · Cited by 53
Self-citationMarkov Data-Based LQG Control1
Shi, G., & Skelton, R. E. (1998) · Journal of Dynamic Systems Measurement and Control · doi:10.1115/1.1286868 · Cited by 49
Vamvoudakis, K. G., Vrabie, D., & Lewis, F. L. (2009) · IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning · doi:10.1109/adprl.2009.4927523 · Cited by 46
Self-citationOptimal design of adaptive tracking controllers for nonlinear systems
Li, Z., & Krstić, M. (1997) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.1997.609721 · Cited by 36
State-Space System Identification with Identified Hankel Matrix
Lim, R. K., Phan, M. Q., & Longman, R. W. (1998) · Cited by 28
Unifying Input-Output and State-Space Perspectives of Predictive Control
Phan, M. Q., Lim, R. K., & Longman, R. W. (1998) · Cited by 26
Identification of a Multistep-Ahead Observer and Its Application to Predictive Control
Lim, R. K., & Phan, M. Q. (1997) · Journal of Guidance Control and Dynamics · doi:10.2514/2.4177 · Cited by 20
Suppressing non-periodically repeating disturbances in mechanical servo systems
Tousain, R. L., Boissy, J.-C., Norg, M. L., Steinbuch, M., & Bosgra, O. H. (2002) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.1998.757832 · Cited by 15
Minimum time pulse response based control of flexible structures
Bennighof, J. K., Chang, S.-H. M., & Subramaniam, M. (1993) · Journal of Guidance Control and Dynamics · doi:10.2514/3.21095 · Cited by 14
Flagged first, then by citations
Research works printed but not linked: 3
- sutton, 1998, Reinforcement LearningAn Introduction
- werbos, 1992, Handbook of Intelligent Control
- 1992, Handbook of Intelligent Control
Cited by
Sorted by citations
Lewis, F. L., Vrabie, D., & Vamvoudakis, K. G. (2012) · IEEE Control Systems · doi:10.1109/mcs.2012.2214134 · Cited by 1,122
Self-citationJiang, Y., & Jiang, Z. (2012) · Automatica · doi:10.1016/j.automatica.2012.06.096 · Cited by 1,079
Health behavior models in the age of mobile interventions: are our theories up to the task?
Riley, W. T., Rivera, D. E., Atienza, A. A., Nilsen, W., Allison, S. M., & Mermelstein, R. (2011) · Translational Behavioral Medicine · doi:10.1007/s13142-011-0021-7 · Cited by 978
Optimal and Autonomous Control Using Reinforcement Learning: A Survey
Kiumarsi, B., Vamvoudakis, K. G., Modares, H., & Lewis, F. L. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2773458 · Cited by 924
Self-citationZhang, H., Cui, L., Zhang, X., & Luo, Y. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2011.2168538 · Cited by 645
Metadata
- Authors
- Lewis, F. L., & Vamvoudakis, K. G.
- Affiliations
- The University of Texas at Arlington (US)
- Venue
- IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Published
- 2011-02
- Volume
- 41
- Issue
- 1
- Pages
- 14-25
- ISSN
- 1083-4419 (ISSN-L)
- 1941-0492
- OpenAlex
- W2151966330
- Cited by
- 544
- References
- 48
- Citations by year
- 2026: 22 · 2025: 49 · 2024: 46 · 2023: 43 · 2022: 37 · 2021: 49 · 2020: 53 · 2019: 34 · 2018: 52 · 2017: 26 · 2016: 35 · 2015: 19 · 2014: 33 · 2013: 18 · 2012: 19
- FWCI
- 15.12
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Adaptive Dynamic Programming Control
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Advanced Control Systems Optimization
- Keywords
- approximate dynamic programming, partially observable Markov decision processes, output feedback control, linear dynamical systems, policy iteration, value iteration, Q-learning, observability index
- MeSH terms
- Algorithms, Artificial Intelligence, Feedback, Learning, Markov Chains, Reinforcement, Psychology
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
