Residual-gradient-based neural reinforcement learning for the optimal control of an acrobot

IEEE International Symposium on Intelligent Control - Proceedings

Volumn , Issue , 2002, Pages 758-763

  Xu, Xin ^a   He, Han Gen ^a  

^a NATIONAL UNIVERSITY OF DEFENSE TECHNOLOGY   (China)

Author keywords

Learning control; Reinforcement learning; Residual gradient; Under actuated robots

Indexed keywords

COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; INTELLIGENT ROBOTS; LEARNING ALGORITHMS; ROBOT LEARNING; TIME VARYING CONTROL SYSTEMS;

ACROBOT; LEARNING CONTROL; REINFORCEMENT LEARNING; UNDERACTUATED ROBOTS;

OPTIMAL CONTROL SYSTEMS;

EID: 0036911781     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. L.P.Kaelbling, M.L Littman, A.W.Moore. Reinforcement Learning :A Survey. Journal of Artificial Intelligence Research, Vol.4., pp:237-285, 1996.
2. L.C.Baird. Residual algorithms: Reinforcement learning with function approximation. Proc. International Conf. On Machine Learning'95. 1995, Morgan Kaufman, San Francisco, CA.
3. L.C. Baird. Gradient descent for general reinforcement learning. M. S. Kearns, S. A. Solla, and D. A. Cohn, editors, Advances in NeuralInformation Processing Systems 11, 1999, MIT Press, Cambridge, MA.
4. M. Heger. The Loss From Imperfect Value Functions in Expectation-Based and Minimax-Based Tasks. Machine Learning, 22, pp. 197-225, 1996.
5. R. Sutton. Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding. Advances in Neural Information Processing Systems 8, 1996, MIT Press, pp: 1038-1044.
6. C. Watkins, P. Dayan. Q-Learning, Machine Learning, Vol. 8, pp. 279-292, 1992.
7. G. Gorden. Stable function approximation in dynamic programming. Proc. Of International Conference on Machine Learning (ML95). 1995, Morgan Kaufman, San Francisco, CA.
8. D. P. Bertsekas and J. N. Tsitsiklis. Gradient convergence in gradient methods, SIAM J. on Optimization, Vol. 10, pp. 627-642, 2000
9. J. Hauser, R.M. Murray. Nonlinear controllers for non-integratable systems: the acrobot example. Proc. Of American Control Conference, San Diego, USA, 1990, pp. 669-671.
10. S. Bortoff, M.W. Spong, Psedolinearization of the acrobot using spline functions. Proc. Of the IEEE Conf. On Decision and Control, Teuson, Arizona, 1992, pp. 593-598.
11. M.W. Spong. The swing up control problem for the acrobot. IEEE Control System Magazine, 15(1), pp. 49-55, 1995.
12. S. Singh, T. Jaakkola, M.L. Littman and C. Szepesvari Convergence Results for Single-step On-policy Reinforcement-learning Algorithms. Machine Learning, Vol. 38, pp. 287-308, 2000.
13. R. Sutton, D. McAllester, S. Singh, Y. Mansour. Policy gradient methods for reinforcement learning with function approximation. Advances in NIPS 12, 1999, pp. 1057-1063, MIT Press.
14. J.N. Tsitsiklis and B.V. Roy. An analysis of Temporal Difference Learning with Function Approximation. IEEE Transactions on Automatic Control. 42(5), pp. 674-690, 1997.