Adaptive Dynamic Programming. Murray, J., Cox, C., Lendaris, G., & Saeks, R. IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 32(2):140–153, May, 2002.
Adaptive Dynamic Programming [link]Paper  doi  abstract   bibtex   
An Adaptive Dynamic Programming algorithm for nonlinear systems with unknown dynamics is developed. The algorithm is initialized with a positive definite cost functional / stabilizing control law pair (V0, k0) (coupled via the Hamilton Jacobi Bellman Equation). Given (Vi, ki), one runs the system using control law ki recording the state and control trajectories, with these trajectories used to define Vi+1 as the cost to take the initial state x0 to the final state using control law, ki, while ki+1 is taken to be the control law derived from Vi+1 via Hamilton Jacobi Bellman Equation.
@article{murray_adaptive_2002,
	title = {Adaptive {Dynamic} {Programming}},
	volume = {32},
	issn = {1094-6977},
	url = {http://ieeexplore.ieee.org/document/1039198/},
	doi = {10.1109/tsmcc.2002.801727},
	abstract = {An Adaptive Dynamic Programming algorithm for nonlinear systems with unknown dynamics is developed. The algorithm is initialized with a positive definite cost functional / stabilizing control law pair (V0, k0) (coupled via the Hamilton Jacobi Bellman Equation). Given (Vi, ki), one runs the system using control law ki recording the state and control trajectories, with these trajectories used to define Vi+1 as the cost to take the initial state x0 to the final state using control law, ki, while ki+1 is taken to be the control law derived from Vi+1 via Hamilton Jacobi Bellman Equation.},
	language = {en},
	number = {2},
	urldate = {2022-02-03},
	journal = {IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews)},
	author = {Murray, J.J. and Cox, C.J. and Lendaris, G.G. and Saeks, R.},
	month = may,
	year = {2002},
	keywords = {/unread},
	pages = {140--153},
}

Downloads: 0