Strategy Learning with Multilayer Connectionist Representations
DOI: 10.1016/B978-0-934613-41-5.50014-3
关键词: Formalism (philosophy of mathematics) 、 The Symbolic 、 Artificial intelligence 、 Connectionism 、 Computer science
摘要: Results are presented the demonstrate learning and fine-tuning of search strategies using connectionist mechanisms. Previous studies strategy within symbolic, production-rule formalism have not addressed behavior. Here a two-layer system is that develops its from weak to task-specific fine-tunes performance. The applied simulated, real-time, balance-control task. We compare performance one-layer networks, showing ability network discover new features thus enhance original representation critical solving balancing
sci-hub.se 参考文章(12)
Andrew G. Barto, Richard S. Sutton, Oliver G. Selfridge, Training and tracking in robotics international joint conference on artificial intelligence. pp. 670- 672 ,(1985)
J.M. Mendel, R.W. McLaren, Reinforcement-learning control and pattern recognition systems Mathematics in science and engineering. ,vol. 66, pp. 287- 318 ,(1994) , 10.1016/S0076-5392(08)60497-X
Barto Ag, Learning by statistical cooperation of self-interested neuron-like computing elements. Human neurobiology. ,vol. 4, pp. 229- 256 ,(1985)
Charles W. Anderson, Learning and Problem Solving with Multilayer Connectionist Systems University Microfilms International. ,(1986)
Patrick W. Langley, Learning to search : from weak methods to domain-specific heuristics Cognitive Science. ,vol. 9, pp. 217- 260 ,(1985) , 10.1016/S0364-0213(85)80015-X
Kumpati S. Narendra, M. A. L. Thathachar, Learning Automata - A Survey IEEE Transactions on Systems, Man, and Cybernetics. ,vol. SMC-4, pp. 323- 334 ,(1974) , 10.1109/TSMC.1974.5408453
Andrew G. Barto, Richard S. Sutton, Charles W. Anderson, Neuronlike adaptive elements that can solve difficult learning control problems systems man and cybernetics. ,vol. 13, pp. 834- 846 ,(1983) , 10.1109/TSMC.1983.6313077
Andrew G. Barto, Richard S. Sutton, Peter S. Brouwer, Associative search network: A reinforcement learning associative memory Biological Cybernetics. ,vol. 40, pp. 201- 211 ,(1981) , 10.1007/BF00453370
Ka Cheok, Nan Loh, A ball balancing demonstration of optimal and disturbance-accomodating control IEEE Control Systems Magazine. ,vol. 7, pp. 54- 57 ,(1987) , 10.1109/MCS.1987.1105235
A. L. Samuel, Some studies in machine learning using the game of checkers Ibm Journal of Research and Development. ,vol. 44, pp. 206- 226 ,(2000) , 10.1147/RD.441.0206