Boots – shoes – and leggings
Patent
1992-03-27
1995-09-05
MacDonald, Allen R.
Boots, shoes, and leggings
395 22, 395906, 395907, 364152, G06F 1518
Patent
active
054486815
ABSTRACT:
A plant controller using reinforcement learning for controlling a plant includes action and critic networks with enhanced learning for generating a plant control signal. Learning is enhanced within the action network by using a neural network configured to operate according to unsupervised learning techniques based upon a Kohonen Feature Map. Learning is enhanced within the critic network by using a distance parameter which represents the difference between the actual and desired states of the quantitative performance, or output, of the plant when generating the reinforcement signal for the action network.
REFERENCES:
patent: 4563746 (1986-01-01), Yoshida et al.
patent: 5058180 (1991-10-01), Khan
patent: 5142612 (1992-08-01), Sheirik
patent: 5175797 (1992-12-01), Funabashi et al.
patent: 5195172 (1993-03-01), Elad et al.
patent: 5201026 (1993-04-01), Tsuiki
patent: 5235339 (1993-08-01), Morrison et al.
patent: 5239593 (1993-08-01), Wittner et al.
patent: 5276771 (1994-01-01), Manukian et al.
patent: 5351200 (1994-09-01), Impink, Jr.
Demetri Psaltis and Athanasius sideris and Alan A. Yamamura; "A Multi-Layered Neural Network Controller"; IEEE Control Systems Magazine; Apr. '88, pp. 18-21.
Allon Guez, James L. Eilbert, and Moshe Kam; "Neural Network Architecture for Control"; IEEE Control Systems Magazine; Apr. 88; pp. 22-25.
Sutton et al, "Reinforcement learning is direct adaptive optimal control"; IEEE Control Systems Magazine, vol. 12, iss. 2, pp. 19-22, Apr. 1992.
Werbos, "An overview of Neural Networks for Control"; IEEE Control Systems Magazine, vol. 11, iss. 1, pp. 40-41, Jan. 1991.
Werbos, "Neural networks for control and system identification"; Proceedings of the 28th IEEE Conference on Decision and Control, pp. 260-265 vol. 1, 13-15 Dec. 1989.
Jameson, "A Neurocontroller based on model feedback and the adaptive heuristic critic"; IJCNN, vol. 2, pp. 37-44, 17-21 Jun. 1990.
Lin et al, "CMAC-based adaptive critic self-learning control"; IEEE Transactions on Neural Networks, vol. 2, iss. 5, pp. 530-533, Sep. 1991.
C. W. Anderson, "Strategy Learning with Multi Layer Connectionist Representations", TR87-509.3, May 17, 1988 (corrected version of report published in Proceedings of the Fourth International Workshop on Machine Learning, Irvine, Calif., 1987), pp. 1-12.
Hamid R. Berenji, "Refinement of Approximate Reasoning Based Controllers by Reinforcement Learning", Machine Learning: Proceedings of the Eighth International Workshop, Jun. 27-29, 1991.
D. Rumelhart et al., "Learning Internal Representations by Error Back Propagation", In D. Rumelhart & J. McCelland (Eds.), Parallel Distributed Processing: Explorations in the Microstructures of Cognition, vol. 1, pp. 318-362, MIT Press, 1986.
W. T. Miller, III, et al., (Eds.) "Neural Networks for Control", pp. 37-47 and 67-87, MIT Press, 1990.
J. Hertz et al., "Introduction to the Theory of Neural Computation", pp. 232-246, Addison-Wesley, 1991.
A. G. Barto et al., "Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems", IEEE Transactions on Systems, Man and Cybernetics, SMC--13:834-846, pp. 538-546, 1983.
R. S. Sutton, "Temporal Credit Assignment in Reinforcement Learning", Ph.D. thesis, University of Massachusetts, 1984.
Hafiz Tariq
MacDonald Allen R.
National Semiconductor Corporation
Nelson H. Donald
Roddy Richard J.
LandOfFree
Intelligent controller with neural network and reinforcement lea does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Intelligent controller with neural network and reinforcement lea, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Intelligent controller with neural network and reinforcement lea will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-479831