Abstract
This chapter presents a Hamiltonian-driven framework of adaptive dynamic programming (ADP) for continuous-time nonlinear systems. Three fundamental problems for solving the optimal control problem are presented, i.e., the evaluation of given admissible policy, the comparison between two different admissible policies with respect to the performance, and the performance improvement of given admissible control. It is shown that the Hamiltonian functional can be viewed as the temporal difference for dynamical systems in continuous time. Therefore, the minimization of the Hamiltonian functional is equivalent to the value function approximation. An iterative algorithm starting from an arbitrary admissible control is presented for the optimal control approximation with its convergence proof. The Hamiltonian-driven ADP algorithm can be implemented using a critic only structure, which is trained to approximate the optimal value gradient. Simulation example is conducted to verify the effectiveness of Hamiltonian-driven ADP.
This work was supported in part by the National Natural Science Foundation of China under Grant No. 61903028, in part by the China Post-Doctoral Science Foundation under Grant 2018M641197, in part by the Fundamental Research Funds for the Central Universities under grant No. FRF-TP-18-031A1 and No. FRF-BD-17-002A, in part by the DARPA/Microsystems Technology Office and in part by the Army Research Laboratory under grant No. W911NF-18-2-0260. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abu-Khalaf, M., Lewis, F.L.: Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network hjb approach. Automatica 41(5), 779–791 (2005)
Bellman, R.: Dynamic Programming. Princeton University Press, Princeton, NJ, USA (1957)
Dimitri, P.: Bertsekas. Nonlinear programming, Athena Scientific, Belmont, MA (1995)
Bertsekas, D.P.: Dynamic programming and optimal control, 3rd edn., vol. 1, Athena Scientific, Belmont, MA (2007)
Fairbank, M., Alonso, E.: Value-gradient learning. In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2012)
Hadda, W., Chellaboina, V.: Nonlinear dynamical systems and control (2008)
Jiang, Yu., Jiang, Z.-P.: Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics. Automatica 48(10), 2699–2704 (2012)
Orrin Frink, J.R.: Differentiation of sequences. Bull. Am. Math. Soc. 41, 553–560 (1935)
Kiumarsi, B., Vamvoudakis, K.G., Modares, H., Lewis, F.L.: Optimal and autonomous control using reinforcement learning: a survey. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2042–2062 (2018)
Kiumarsi, B., Lewis, F.L., Jiang, Z.-P.: H\(_\infty \) control of linear discrete-time systems: Off-policy reinforcement learning. Automatica 78, 144–152 (2017)
Lewis, F.L., Liu, D.: Reinforcement learning and approximate dynamic programming for feedback control, vol. 17. Wiley, Hoboken (2013)
Lewis, F.L., Vrabie, D.: Reinforcement learning and adaptive dynamic programming for feedback control. Circuits Syst. Mag. IEEE 9(3), 32–50 (2009)
Lewis, F.L., Vrabie, D., Vamvoudakis, K.G.: Reinforcement learning and feedback control: using natural decision methods to design optimal adaptive controllers. IEEE Control Syst. 32(6), 76–105 (2012)
Daniel, L.: Calculus of variations and optimal control theory: a concise introduction. Princeton University Press, Princeton (2012)
Biao, L., Wu, H.-N., Tingwen, H.: Off-policy reinforcement learning for control design. IEEE Trans. Cybern. 45(1), 65–76 (2015)
Miller, W.T., Werbos, P.J., Sutton, R.S.: Neural networks for control. MIT press, Cambridge (1995)
Modares, H., Lewis, F.L.: Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning. Automatica 50(7), 1780–1792 (2014)
Modares, H., Lewis, F.L., Jiang, Z.-P.: Tracking control of completely unknown continuous-time systems via off-policy reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 26(10), 2550–2562 (2015)
Modares, H., Lewis, F.L., Naghibi-Sistani, M.-B.: Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems. Automatica 50(1), 193–202 (2014)
Murray, J.J., Cox, C.J., Lendaris, G.G., Saeks, R.: Adaptive dynamic programming. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 32(2), 140–153 (2002)
Padhi, R., Unnikrishnan, N., Wang, X., Balakrishnan, S.N.: A single network adaptive critic (snac) architecture for optimal control synthesis for a class of nonlinear systems. Neural Netw. 19(10), 1648–1660 (2006)
Lev Semenovich Pontryagin.: Mathematical theory of optimal processes. CRC Press, Boca Raton (1987)
Prokhorov, D.V., Wunsch, D.C., et al.: Adaptive critic designs. Neural Netw. IEEE Trans. 8(5), 997–1007 (1997)
Saridis, G.N., Lee, C.-S.G.: An approximation theory of optimal control for trainable manipulators. IEEE Trans. Syst. Man Cybern. 9(3), 152–159 (1979)
Speyer, J.L., Jacobson, D.H.: Primer on optimal control theory, vol. 20. SIAM, Philadelphia (2010)
Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3(1), 9–44 (1988)
Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction, vol. 1, MIT Press, Cambridge (1998)
Vamvoudakis, K.G., Ferraz, H.: Model-free event-triggered control algorithm for continuous-time linear systems with optimal performance. Automatica 87, 412–420 (2018)
Vamvoudakis, K.G., Lewis, F.L.: Online actor–critic algorithm to solve the continuous-time infinite horizon optimal control problem. Automatica 46(5), 878–888 (2010)
Van der Schaft, A.J.: L2-gain analysis of nonlinear systems and nonlinear state-feedback h control. IEEE Trans. Autom. Control 37(6), 770–784 (1992)
Vrabie, D., Lewis, F.: Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems. Neural Netw. 22(3), 237–246 (2009)
Wang, F.-Y., Zhang, H., Liu, D.: Adaptive dynamic programming: an introduction. IEEE Comput. Intell. Mag. 4(2), 39–47 (2009)
Werbos, P.J.: Beyond regression: new tools for prediction and analysis in the behavioral sciences. Ph.D. thesis, Harvard (1974)
Paul John Werbos: Consistency of hdp applied to a simple reinforcement learning problem. Neural Netw. 3(2), 179–189 (1990)
Paul John Werbos: Approximate dynamic programming for real-time control and neural modeling. Handb. Intell. Control.: Neural Fuzzy Adapt. Approaches 15, 493–525 (1992)
Werbos, P.J.: The roots of backpropagation: from ordered derivatives to neural networks and political forecasting, vol. 1. Wiley, Hoboken (1994)
White, D.A., Sofge, D.A.: Handbook of intelligent control: neural, fuzzy, and adaptative approaches. Van Nostrand Reinhold Company, New York (1992)
Yang, Y., Guo, Z.-S., Haoyi Xiong, Z.-S., Ding, D.-W., Yin, Y., Wunsch, D.C.: Data-driven robust control of discrete-time uncertain linear systems via off-policy reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. (2019)
Yang, Y., Modares, H., Wunsch, D.C., Yin, Y.: Leader-follower output synchronization of linear heterogeneous systems with active leader using reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2139–2153 (2018)
Yang, Y.: Optimal containment control of unknown heterogeneous systems with active leaders. IEEE Trans. Control Syst. Technol. 27(3), 1228–1236 (2019)
Yang, Y., Vamvoudakis, K.G., Ferraz, H., Modares, H.: Dynamic intermittent Q-learning-based model-free suboptimal co-design of L\(_2\)-stabilization. Int. J. Robust Nonlinear Control 29(9), 2673–2694 (2019)
Yang, Y., Wunsch, D.C., Yin, Y.: Hamiltonian-driven adaptive dynamic programming for continuous nonlinear dynamical systems. IEEE Trans. Neural Netw. Learn. Syst. 28(8), 1929–1940 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Yang, Y., Wunsch II, D.C., Yin, Y. (2021). Adaptive Dynamic Programming in the Hamiltonian-Driven Framework. In: Vamvoudakis, K.G., Wan, Y., Lewis, F.L., Cansever, D. (eds) Handbook of Reinforcement Learning and Control. Studies in Systems, Decision and Control, vol 325. Springer, Cham. https://doi.org/10.1007/978-3-030-60990-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-60990-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60989-4
Online ISBN: 978-3-030-60990-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)