Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence Proof
作者： A. Al-Tamimi , F.L. Lewis , M. Abu-Khalaf
DOI: 10.1109/TSMCB.2008.926614
关键词:
摘要: 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 …
acm.org
sci-hub.se 参考文章(35)
W Thomas Miller, Richard S Sutton, Paul J Werbos, A menu of designs for reinforcement learning over time Neural networks for control. pp. 67- 95 ,(1990)
Wei Lin, C.I. Byrnes, H/sub /spl infin//-control of discrete-time nonlinear systems IEEE Transactions on Automatic Control. ,vol. 41, pp. 494- 510 ,(1996) , 10.1109/9.489271
SHG ten Hagen, Ben JA Kröse, None, Linear Quadratic Regulation using reinforcement learning Proc. of the 8th Belgian-dutch Conf. on machine learning BENELEARN-98. pp. 39- 46 ,(1998)
Tomas Landelius, Reinforcement Learning and Distributed Local Model Synthesis ,(1997)
F W Lewis, S. Jagannathan, A Yesildirak, Neural Network Control of Robot Manipulators and Nonlinear Systems CRC Press. ,(1998) , 10.1201/9781003062714
ModelBased Adaptive Critic Designs Handbook of Learning and Approximate Dynamic Programming. pp. 65- 95 ,(2004) , 10.1109/9780470544785.CH3
John N. Tsitsiklis, Dimitri P. Bertsekas, Neuro-dynamic programming ,(1996)
L. Rodman, Peter Lancaster, Algebraic Riccati equations ,(1995)
Bruce A. Finlayson, The method of weighted residuals and variational principles ,(1972)
S.J. Bradtke, B.E. Ydstie, A.G. Barto, Adaptive linear quadratic control using policy iteration advances in computing and communications. ,vol. 3, pp. 3475- 3479 ,(1994) , 10.1109/ACC.1994.735224