Toward effective combination of off-line and on-line training in ADP framework

Proceedings of the 2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007

Volumn , Issue , 2007, Pages 268-271

  Prokhorov, Danil ^a  

^a TOYOTA TECHNICAL CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL METHODS; KALMAN FILTERS; REAL TIME SYSTEMS; RECURRENT NEURAL NETWORKS; REINFORCEMENT LEARNING; ROBUSTNESS (CONTROL SYSTEMS);

MULTISTREAM KALMAN FILTER METHOD; OFF-LINE METHODS; RESEMBLING REINFORCEMENT;

DYNAMIC PROGRAMMING;

EID: 34548777734     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ADPRL.2007.368198     Document Type: Conference Paper

References (16)

1. L. A. Feldkamp, D. V. Prokhorov, C. F. Eagen, and F. Yuan, "Enhanced multi-stream Kalman filter training for recurrent networks," in J. Suykens and J. Vandewalle (eds), Nonlinear Modeling: Advanced Black-Box Techniques, Kluwer Academic Publishers, 1998., pp. 29-53.
2. D. V. Prokhorov, G. V. Puskorius, and L. A. Feldkamp, "Dynamical neural networks for control," see in A Field Guide to Dynamical Recurrent Networks, J. Kolen and S. Kremer (Eds.), IEEE Press, 2001, pp. 257-289.
3. D. Prokhorov, "Training Recurrent Neurocontrollers for Robustness with Derivative-Free Kalman Filter," IEEE Trans. Neural Networks, November 2006, pp. 1606-1616.
4. D. Prokhorov, "Training Recurrent Neurocontrollers for Real-Time Applications," IEEE Trans. Neural Networks, to appear.
5. M. Kawato, Y Uno, M. Isobe, and R. Suzuki, "Hierarchical neural network model for voluntary movement with application to robotics," IEEE Control Systems Magazine, vol. 8, no. 2, April 1988, pp. 8-15.
6. J. Suykens, J. Vandewalle, and B. De Moor, Artificial Neural Networks for Modeling and Control of Non-Linear Systems, Kluwer Academic, 1996.
7. Publications of Paul J. Werbos at www.werbos.com.
8. L.-J. Lin and T. Mitchell, Memory Approaches To Reinforcement Learning In Non-Markovian Domains, Technical Report CMU-CS-92-138, School of Computer Science, Carnegie Mellon University, May 1992.
9. P. Eaton, D. Prokhorov, and D. Wunsch, "Neurocontroller Alternatives for Fuzzy Ball-and-Beam Systems with Nonlinear, Nonuniform Friction," IEEE Trans. on Neural Networks, March 2000, pp. 423-435.
10. K. Bush and C. Anderson, "Modeling Reward Functions for Incomplete State Representations via Echo State Networks," Proceedings of the International Joint Conference on Neural Networks, Montreal, Canada, August 1-4, 2005.
11. B. Bakker, "Reinforcement learning by backpropagation through an LSTM model/critic," Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, Honolulu, Hawaii, April 1-5, 2007.
12. L. Feldkamp and D. Prokhorov, "Observations on the Practical Use of Derivative Adaptive Critics," Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), Orlando, FL, October 1997, pp. 3061-3066.
13. D. Prokhorov, "Backpropagation through time and derivative adaptive critics: a common framework for comparison," Chapter 15 in Handbook of Learning and Approximate Dynamic Programming, J. Si et al. (eds), IEEE Press, 2004.
14. H. Jaeger and H. Haas, "Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless telecommunications," Science, April 2, 2004, pp. 78-80.
15. E. Micheli-Tzanakou, Supervised and Unsupervised Pattern Recognition: Feature Extraction in Computational Intelligence, CRC Press, 2000.
16. J. C. Spall and J. A. Cristion, "Model-free control of nonlinear stochastic systems with discrete-time measurements," IEEE Trans. Automatic Control, vol. 43, no. 9, September 1998, pp. 1198-1210.