Partitioning input space for reinforcement learning for control

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 2, Issue , 1997, Pages 755-760

  Hougen, D F ^a   Gini, M ^a   Slagle, J ^a  

^a University of Minnesota   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

INPUT SPACE; SYSTEM DESIGNERS; SYSTEM LEARNING; TEMPORAL DOMAIN;

NEURAL NETWORKS; REINFORCEMENT LEARNING; CONTROL THEORY; ELECTRIC NETWORK TOPOLOGY;

PARTITIONS (BUILDING); LEARNING SYSTEMS;

INPUT SPACE PARTITIONING; REINFORCEMENT LEARNING;

EID: 0030691689     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.616117     Document Type: Conference Paper

References (18)

1. C. W. Anderson. Learning to control an inverted pendulum using neural networks. IEEE Control Systems Magazine, 9(3):31-37,1989.
2. A. R. Barto, R. S. Sutton, and C. W. Anderson. Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans, on Systems, Man, and Cybernetics, SMC-13:834-846,1983.
3. R. E. Bellman. Dynamic Programming. Princeton University Press, Princeton, NJ, 1957.
4. D. F. Hougen. Use of an eligibility trace to self-organize output. In Science of Artificial Neural Networks II, Proc. SPIE, volume 1966, pages 436-447, 1993.
5. D. F. Hougen, J. Fischer, M. Gini, and J. Slagle. Fast connectionist learning for trailer backing using a real robot. In IEEE Int'l Conf. on Robotics and Automation, pages 1917-1922,1996.
6. D. F. Hougen, M. Gini, and J. Slagle. Rapid, unsupervised connectionist learning for backing a robot with two trailers. In IEEE Int'l Conf. on Robotics and Automation, 1997.
7. A. Klopf. Brain function and adaptive systems-A het-erostatic theory. In Proc. of the Int'l Conf. on Systems, Man, and Cybernetics, 1974.
8. T. K. Kohonen. Self-organizing and associative memory. Springer-Verlag, Berlin, 3rd edition, 1989.
9. S.-G. Kong and B. Kosko. Adaptive fuzzy systems for backing up a truck-and-trailer. IEEE Trans, on Neural Networks, 3(2):211-223,1992.
10. T. M. Martinetz, H. J. Ritter, and K. J. Schulten. 3d-neural-net for learning visuomoter-coordination of a robot arm. In Int'l Joint Conf. on Neural Networks, volume II, pages 351-356. Erlbaum, 1989.
11. D. Michie and R. Chambers. Boxes: an experiment in adaptive control. In E. Dale and D. Michie, editors, Machine Intelligence. Oliver and Boyd, Edinburgh, 1968.
12. A. W. Moore and C. G. Atkeson. The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spaces. Machine Learning, 21:199-233,1995.
13. H. Ritter, T. Martinetz, and K. Schulten. Neural computation and self-organizing maps: an introduction. Addison-Wesley, Reading, MA, 1992.
14. B. E. Rosen, J. M. Goodwin, and J. J. Vidal. Process control with adaptive range coding. Biological Cybernetics, 66:419-428,1992.
15. J. Simons, H. V. Brussel, J. D. Schutter, and J. Ver-haert. A self-learning automaton with variable resulu-tion for high precision assembly by industrial robots. IEEE Trans, on Automatic Control, 27(5): 1109-1113, October 1982.
16. S. P. Singh and R. S. Sutton. Reinforcement learning with replacing eligibility traces. Machine Learning, 22:123-158,1996.
17. R. S. Sutton. Learning to predict by the methods of temporal differences. Machine Learning, 3:944, 1988.
18. N. Woodcock, N. J. Hallam, and P. D.Picton. Fuzzy BOXES as an alternative to neural networks for difficult control problems. Artificial Inteligence in Engineering, pages 903-919,1991.