Learning to Control an Inverted Pendulum Using Neural Networks

IEEE Control Systems Magazine

Volumn 9, Issue 3, 1989, Pages 31-37

  Anderson, Charles W ^a  

^a VERIZON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DYNAMICS; PENDULUMS--CONTROL;

CONTROLLERS; INVERTED PENDULUMS; NEURAL NETWORKS; REINFORCEMENT LEARNING METHOD; TEMPORAL DIFFERENCE LEARNING METHOD;

SYSTEMS SCIENCE AND CYBERNETICS;

EID: 0024646143     PISSN: 02721708     EISSN: None     Source Type: Journal    
DOI: 10.1109/37.24809     Document Type: Article

References (23)

1. K. C. Cheok and N. K. Loh, “A Ball-Balancing Demonstration of Optimal and Disturbance-Accommodating Control,” IEEE Contr. Syst. Mag., vol. 7, no. 1, pp. 54-57, Feb. 1987.
2. E. Eastwood, “Control Theory and the Engineer,” Proc. IEE, vol. 115, no. 1, pp. 203-211, Jan. 1968.
3. R. H. Cannon, Jr., Dynamics of Physical Systems, McGraw-Hill, 1967.
4. J. K. Roberge, “The Mechanical Seal,” S.B. Thesis, Massachusetts Institute of Technology, Cambridge, MA, May 1960.
5. A. G. Barto, R. S. Sutton, and C. W. Anderson, “Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems,” IEEE Trans. Syst., Man, Cybern., vol. SMC-13, pp. 834-846, Sept.-Oct. 1983.
6. C. W. Anderson, “Strategy Learning with Multilayer Connectionist Representations,” Tech. Rept. TR87-509.3, GTE Laboratories, Waltham, MA, 1987. (This is a corrected version of the report published in Proc. Fourth International Workshop on Machine Learning, Irvine, CA, pp. 103-114, June 1987.)
7. B. Widrow and F. W. Smith, “Pattern-Recognizing Control Systems,” 1963 Computer and Information Sciences (COINS) Symp. Proc., Washington, DC: Spartan, pp. 288-317, 1964.
8. B. Widrow, “The Original Adaptive Neural Net Broom-Balancer, ” Int. Symp. Circuits and Syst., pp. 351-357, May 1987.
9. A. Guez and J. Selinsky, “A Trainable Neuromorphic Controller,” J. Robotic Syst., vol. 5, no. 4, pp. 363-388, Aug. 1988.
10. V. V. Tolat and B. Widrow, “An Adaptive ‘Broom Balancer’ with Visual Inputs,” Proc. IEEE Int. Conf. on Neural Networks, San Diego, CA, pp. 11-641-11-647, July 1988.
11. M. E. Connell and P. E. Utgoff, “Learning to Control a Dynamic Physical System,” Proc. AAAI-87, vol. 2, pp. 456-460, American Association for Artificial Intelligence, Seattle, WA, 1987.
12. B. E. Rosen, J. M. Goodwin, and J. J. Vidal, “State Recurrence Learning,” First Annual Int. Neural Network Society Meeting, Boston, MA, Sept. 1988 (abstract appears in Neural Networks, vol. 1, Suppl. 1, p. 48, 1988).
13. G. E. Hinton, “Connectionist Learning Procedures,” Tech. Rept. CMU-CS-87-115, Camegie-Mellon Univ., Pittsburgh, PA, 1987; to appear in Artificial Intelligence.
14. R. S. Sutton and A. G. Barto, “Toward a Modem Theory of Adaptive Networks: Expectation and Prediction,” Psychol. Rev., vol. 88, no. 2, pp. 135-170, 1981.
15. R. S. Sutton, “Temporal Credit Assignment in Reinforcement Learning,” Doctoral Dissertation, COINS Tech. Rept. 8402, Univ. of Massachusetts, Amherst, 1984.
16. R. S. Sutton, “Learning to Predict by the Methods of Temporal Differences,” Machine Learning, vol. 3, pp. 9-44, 1988.
17. D. Michie and R. A. Chambers, “BOXES: An Experiment in Adaptive Control,” Machine Intelligence 2, E. Dale and D. Michie, eds., Edinburgh: Oliver and Boyd, pp. 137-152, 1968.
18. D. E. Rumelhart, G. E. Hinton, and R. W. Williams, “Learning Internal Representations by Error Propagation,” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume 1: Foundations, D. E. Rumelhart, J. L. McClelland, and The PDP Research Group, Cambridge, MA: Bradford, 1986.
19. J. J. Helferty, J. B. Collins, and M. Kam, “A Learning Strategy for the Control of a Mobile Robot That Hops and Runs,” Proc. IASTED-88, Galveston, TX, pp. 7-11, International Association of Science and Technology for Development, 1988.
20. J. C. Hoskins and D. M. Himmelblau, “Automatic Chemical Process Control Using Reinforcement Learning in Artificial Neural Networks,” First Annual Int. Neural Network Society Meeting, Boston, MA, Sept. 1988 (abstract appears in Neural Networks, vol. 1, Suppl. 1, p. 446, 1988).
21. W, T. Miller, “Sensor-Based Control of Robotic Manipulators Using a General Learning Algorithm,” IEEE J. Robotics Automat., vol. RA-3, no. 2, pp. 157-165, Apr. 1987.
22. J. A. Franklin, “Learning Control in a Robotic System,” Proc. IEEE Int. Conf. Syst., Man, Cybern., Alexandria, VA, pp. 466-470, Oct. 1987.
23. O. G. Selfridge, R. S. Sutton, and A. G. Barto “Training and Tracking in Robotics,” Proc. IJCAI-85, pp. 670-672.