Integral reinforcement learning for online computation of feedback Nash strategies of nonzero-sum differential games

Proceedings of the IEEE Conference on Decision and Control

Volumn , Issue , 2010, Pages 3066-3071

  Vrabie, Draguna ^a   Lewis, Frank ^a  

^a UNIVERSITY OF TEXAS AT ARLINGTON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGEBRA; CONTINUOUS TIME SYSTEMS; DYNAMIC PROGRAMMING; FEEDBACK; GAME THEORY; ITERATIVE METHODS; REINFORCEMENT LEARNING; RICCATI EQUATIONS; SYSTEM THEORY;

CONTROL STRATEGIES; COUPLED ALGEBRAIC RICCATI EQUATIONS; DIFFERENTIAL GAMES; INFINITE HORIZONS; NONZERO-SUM DIFFERENTIAL GAME; OFF-LINE METHODS; ON-LINE ALGORITHMS; ONLINE COMPUTATIONS;

E-LEARNING;

EID: 79953133535     PISSN: 07431546     EISSN: 25762370     Source Type: Conference Proceeding    
DOI: 10.1109/CDC.2010.5718152     Document Type: Conference Paper

References (24)

1. Abou-Kandil, H., Freiling, G., Jank, G., "Necessary and sufficient conditions for constant solutions of coupled Riccati equations in Nash games", Systems and Control Letters, 21, 2003, pp. 295-306.
2. nd ed., (Classics in Applied Mathematics; 23), SIAM, 1999.
3. Beard, R., Saridis, G., & Wen, J., "Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equation". Automatica, 33(11), pp. 2159-2177, 1997.
4. Bertsekas D. P. and Tsitsiklis J. N., Neuro-Dynamic Programming, Athena Scientific, MA, 1996.
5. Brewer J. W., "Kronecker Products and Matrix Calculus in System Theory", IEEE Trans. on Circuit and System, 25(9), 1978, pp. 772-781.
6. Cherfi L., Abou-Kandil H., Bourles H., "Iterative method for general algebraic Riccati equation", Proc. ACSE'05, 2005.
7. Cherfi L., Chitour Y., Abou-Kandil H., "A new algorithm for solving coupled algebraic Riccati equations", Proc. of CIMCA'05, 2005, pp. 83-88.
8. Engwerda J.C., LQ dynamic optimization and differential games, Chichester: Wiley, 2005.
9. Freiling G., Jank G., Abou-Kandil H., "On Global Existence of Solutions to Coupled Matrix Riccati Equations in Closed-Loop Nash Games", IEEE Transaction on Automatic Control, 41(2), 1996, pp.264-269.
10. Hanselmann T., Noakes L., and Zaknich A., "Continuous-time adaptive critics", IEEE Transactions on Neural Networks, 18(3), 631-647, 2007. (Pubitemid 46778095)
11. Jungers M., De Pieri E., Abou-Kandil H., "Solving Coupled Riccati Equations for Closed-Loop Nash Strategy, by Lack of Trust Approach", International Journal of Tomography and Statistics, 7(F07), 2007, pp. 49-54.
12. Kleinman D., "On an Iterative Technique for Riccati Equation Computations", IEEE Trans. on Automatic Control, February, 1968.
13. Li, T. and Gajic, Z., "Lyapunov iterations for solving coupled algebraic Riccati equations of Nash differential games and algebraic Riccati equations of zero-sum games", in New Trends in Dynamic Games, G. Olsder (ed.), Birkhauser, 1995, pp. 333-351.
14. Mukaidani, H., "Optimal numerical strategy for Nash games of weakly coupled large scale systems", Dynamics of Continuous, Discrete and Impulsive Systems, Series B: Applications and Algorithms, 13, 2006, pp. 249-268.
15. Mukaidani, H., "Newton's method for solving cross-coupled sign-indefinite algebraic Riccati equations for weakly coupled large-scale systems", Applied Mathematics and Computation, 188, 2007, pp. 103-115.
16. Mukaidani, H., "Numerical computation of sign-indefinite linear quadratic differential games for weakly coupled large scale systems", International Journal of Control, 80(1), 2007, pp. 75-86.
17. Prokhorov D., Wunsch D., "Adaptive critic designs," IEEE Trans. on Neural Networks, 8(5), 997-1007, 1997.
18. Shah, V., Power control for wireless data services based on utility and pricing, M.S. thesis, Rutgers University, 1998.
19. Starr, A. and Y. Ho, "Nonzero-sum differential games", J. Optimization Theory and Applications, 3(3), 1969, pp. 184-206.
20. Sutton, R., "Learning to predict by the method of temporal differences," Machine Learning, 3:9-44, 1988.
21. Vrabie D., Pastravanu O., Lewis F., Abu-Khalaf M., "Adaptive Optimal Control for Continuous-Time Linear Systems Based on Policy Iteration", Automatica, 45(2), 2009, pp. 477-484.
22. Watkins, C., Learning from Delayed Rewards, Ph.D. Thesis, Cambridge University, Cambridge, England, 1989.
23. Werbos, P. J., "Approximate dynamic programming for real-time control and neural modeling". In Handbook of Intelligent Control, Neural, Fuzzy, and, Adaptive Approaches, White, D. and Sofge D., Eds., New York: Van Nostrand, 1992.
24. Wei Q. and Zhang H., "A new approach to solve a class of continuous-time nonlinear quadratic zero-sum game using ADP", Proc. IEEE International Conference on Networking, Sensing and Control (ICNSC'08), 6(8) 2008, pp. 507-512.