The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence Proof
Abstract
Convergence of the value-iteration-based heuristic dynamic programming (HDP) algorithm is proven in the case of general nonlinear systems. That is, it is shown that HDP converges to the optimal control and the optimal value function that solves the Hamilton-Jacobi-Bellman equation appearing in infinite-horizon discrete-time (DT) nonlinear optimal control. It is assumed that, at each iteration, the value and action update equations can be exactly solved. The following two standard neural networks (NN) are used: a critic NN is used to approximate the value function, whereas an action network is used to approximate the optimal control policy. It is stressed that this approach allows the implementation of HDP without knowing the internal dynamics of the system. The exact solution assumption holds for some classes of nonlinear systems and, specifically, in the specific case of the DT linear quadratic regulator (LQR), where the action is linear and the value quadratic in the states and NNs have zero approximation error. It is stressed that, for the LQR, HDP may be implemented without knowing the system A matrix by using two NNs. This fact is not generally appreciated in the folklore of HDP for the DT LQR, where only one critic NN is generally used.
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
Watkins, C. (1989) · OpenGrey (Institut de l'Information Scientifique et Technique) · doi:10.17863/cam.132164 · Cited by 5,297
(2012) · Encyclopedia of the Sciences of Learning · doi:10.1007/978-1-4419-1428-6_5086 · Cited by 3,515
Dynamic Programming and Markov Processes.
Freimer, M., & Howard, R. A. (1961) · Journal of the American Statistical Association · doi:10.2307/2282268 · Cited by 3,378
Neuronlike adaptive elements that can solve difficult learning control problems
Barto, A. G., Sutton, R. S., & Anderson, C. W. (1983) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1983.6313077 · Cited by 3,233
Aircraft Control and Simulation
Stevens, B., & Lewis, F. L. (2004) · Aircraft Engineering and Aerospace Technology · doi:10.1108/aeat.2004.12776eae.001 · Cited by 3,167
Self-citationHornik, K., Stinchcombe, M., & White, H. (1990) · Neural Networks · doi:10.1016/0893-6080(90)90005-6 · Cited by 2,111
The Method of Weighted Residuals and Variational Principles
Finlayson, B. A. (2013) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611973242 · Cited by 1,945
(2020) · Machine Learning and Visual Perception · doi:10.1515/9783110595567-011 · Cited by 1,930
Neural Network Control Of Robot Manipulators And Non-Linear Systems
Lewis, F. W., Jagannathan, S., & Yesildirak, A. (2020) · CRC Press eBooks · doi:10.1201/9781003062714 · Cited by 1,867
Self-citationAbu-Khalaf, M., & Lewis, F. L. (2005) · Automatica · doi:10.1016/j.automatica.2004.11.034 · Cited by 1,349
Self-citationLancaster, P., & Rodman, L. (1995) · doi:10.1093/oso/9780198537953.001.0001 · Cited by 1,215
Prokhorov, D. V., & Wunsch, D. C. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.623201 · Cited by 1,186
(2006) · Indefinite Linear Algebra and Applications · doi:10.1007/3-7643-7350-4_14 · Cited by 1,115
Approximate dynamic programming for real-time control and neural modeling
Werbos, P. J. (1992) · Medical Entomology and Zoology · Cited by 971
(2011) · Encyclopedia of Machine Learning · doi:10.1007/978-0-387-30164-8_588 · Cited by 950
Handbook of Learning and Approximate Dynamic Programming
Si, J., Barto, A. G., Powell, W. B., & Wunsch, D. (2004) · Institute of Electrical and Electronics Engineers eBooks · doi:10.1109/9780470544785 · Cited by 856
Online learning control by association and reinforcement
Si, J., & Wang, Y.-T. (2001) · IEEE Transactions on Neural Networks · doi:10.1109/72.914523 · Cited by 773
Murray, J. J., Cox, C. J., Lendaris, G. G., & Saeks, R. (2002) · IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews) · doi:10.1109/tsmcc.2002.801727 · Cited by 677
Dynamic Programming and Markov Processes.
Kaufman, H., & Howard, R. A. (1961) · The American Mathematical Monthly · doi:10.2307/2312519 · Cited by 638
Al-Tamimi, A., Lewis, F. L., & Abu-Khalaf, M. (2007) · Automatica · doi:10.1016/j.automatica.2006.09.019 · Cited by 611 · cited 1×
“In our previous work [3], [4], we studied ADP value iteration techniques to solve the zero-sum”
MethodSelf-citationA Menu of Designs for Reinforcement Learning Over Time
Werbos, P. J. (1991) · Neural Networks for Control · doi:10.7551/mitpress/4939.003.0007 · Cited by 605
Кwon, W. H., & Han, S. H. (2005) · Springer eBooks · doi:10.1007/b136204 · Cited by 553
State-dependent Riccati equation techniques: an overview
Cloutier, J. R. (1997) · Proceedings of the 1997 American Control Conference (Cat. No.97CH36041) · doi:10.1109/acc.1997.609663 · Cited by 437
Adaptive linear quadratic control using policy iteration
Bradtke, S. J., Ydstie, B. E., & Barto, A. G. (2005) · Proceedings of 1994 American Control Conference - ACC '94 · doi:10.1109/acc.1994.735224 · Cited by 404
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) · Proceedings of the 28th IEEE Conference on Decision and Control · doi:10.1109/cdc.1989.70114 · Cited by 319
Punish/Reward: Learning with a Critic in Adaptive Threshold Systems
Widrow, B., Gupta, N. K., & Maitra, S. (1973) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1973.4309272 · Cited by 280
Adaptive Critic Designs for Discrete-Time Zero-Sum Games With Application to $H_{\infty}$ Control
Al-Tamimi, A., Abu-Khalaf, M., & Lewis, F. L. (2007) · IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) · doi:10.1109/tsmcb.2006.880135 · Cited by 184
Self-citationH/sub ∞/-control of discrete-time nonlinear systems
Lin, W. T., & Byrnes, C. I. (1996) · IEEE Transactions on Automatic Control · doi:10.1109/9.489271 · Cited by 183
Reinforcement Learning-Based Output Feedback Control of Nonlinear Systems With Input Constraints
He, P., & Jagannathan, S. (2005) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2004.840124 · Cited by 124
Minimax differential dynamic programming: application to a biped walking robot
Morimoto, J., Zeglin, G. J., & Atkeson, C. G. (2003) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2003.1248926 · Cited by 115
Reinforcement Learning and Distributed Local Model Synthesis
Landelius, T. (1997) · Cited by 113
Convergence analysis of adaptive critic based optimal control
Liu, X., & Balakrishnan, S. N. (2000) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2000.879538 · Cited by 80
Introduction to the special issue on neural network feedback control
Narendra, K. S., & Lewis, F. L. (2001) · Automatica · doi:10.1016/s0005-1098(01)00125-x · Cited by 52
Self-citationLinear Quadratic Regulation using reinforcement learning
Hagen, S., & Kröse, B. (1998) · Cited by 35
Hamilton-Jacobi-Isaacs formulation for constrained input nonlinear systems
Abu-Khalaf, M., Lewis, F. L., & Huang, J. (2004) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2004.1429604 · Cited by 25
Self-citationPoole, D. L., & Mackworth, A. K. (2023) · Cambridge University Press eBooks · doi:10.1017/9781009258227.018 · Cited by 24
Cited by
Reinforcement 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 1,558
Self-citation(2012) · IEEE Control Systems · doi:10.1109/mcs.2012.2214134 · Cited by 1,105
Adaptive Dynamic Programming: An Introduction
Wang, F.-Y., Zhang, H., & Liu, D. (2009) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2009.932261 · Cited by 898
Optimal and Autonomous Control Using Reinforcement Learning: A Survey
Kiumarsi, B., Vamvoudakis, K. G., Modares, H., & Lewis, F. L. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2773458 · Cited by 891
Self-citationPolicy Iteration Adaptive Dynamic Programming Algorithm for Discrete-Time Nonlinear Systems
Liu, D., & Wei, Q. (2014) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2281663 · Cited by 753
Metadata
- Authors
- Al-Tamimi, A., Lewis, F. L., & Abu-Khalaf, M.
- Venue
- IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Published
- 2008-08
- Volume
- 38
- Issue
- 4
- Pages
- 943-949
- ISSN
- 1083-4419 (ISSN-L)
- OpenAlex
- W2093831009
- Cited by
- 1,075
- References
- 37
- FWCI
- 39.19
- 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.