A scalable model-free recurrent neural network framework for solving POMDPs

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

Volumn , Issue , 2007, Pages 119-126

  Liu, Zhenzhen ^a,b   Elhanany, Itamar ^a,b  

^a IEEE

^b University of Tennessee

Author keywords

Constraint optimization; Real lime recurrent learning (RTRL); Recurrent neural networks

Indexed keywords

APPROXIMATION THEORY; COMPUTER SIMULATION; FUNCTION EVALUATION; LEARNING ALGORITHMS; PROBLEM SOLVING; SCALABILITY;

CONSTRAINT OPTIMIZATION; ONLINE TRAINING ALGORITHMS; REAL-LIME RECURRENT LEARNING (RTRL); STOCHASTIC META-DESCENT (SMD);

RECURRENT NEURAL NETWORKS;

EID: 34548774723     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ADPRL.2007.368178     Document Type: Conference Paper

References (20)

1. D. Budik and I. Elhanany, "TRTRL; a localized resource-efficient learning algorithm for recurrent neural networks," in IEEE Midwest Symposium on Circuits, and Systems (MWSCAS), August 2006, puerto Rica.
2. A. Delgado, C. Kambhampati, and K. Warwick, "Dynamic recurrent neural network for system identification and control," in IEE Proceedings - Control Theory and Applications.
3. 2) algorithm," in Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on, vol. 6, Istanbul, 2000, pp, 3418-3421.
4. S. E. Fahlman, "An empirical study of learning speed in backpropagation networks," Computer Science Technical Report, 1988.
5. F. J Gomez and J. Schmidhuber, "Co-evolving recurrent neurons learn deep memory pomdps," in GECCO '05: Proceedings of the 2005 conference on Genetic and evolutionary computation. New York, NY, USA. ACM Press, 2005, pp. 491-498.
6. L. Jain, Recurrent Neural Networks. CRC Press, February 2000.
7. J. Kivinen and M. Warmuth, "Exponentiated gradient versus gradient descent for linear predictors," Tech. Rep. UCSC-CRL-94-16, 1994.
8. J. Kivinen and M. K. Warmuth, "Additive versus exponentiated gradient updates for linear prediction," in Proc. of the twenty-seventh annual ACM symposium on Theory of computing, 1995, pp. 209-218.
9. L. Lin and T. Mitchell, "Memory approaches to reinforcement learning in non-Markovian domains," Pittsburgh, PA, USA, Tech. Rep., 1992.
10. G. D. Magoulas, M. N. Vrahatis, and G. S. Androulakis, "Improving the convergence of the backpropagation algorithm using learning rate adaptation methods," Neural Computation, vol. 11, no. 7, pp. 1769-1796, 1999.
11. D. Nguyen and B. Widrow. "Neural networks for self-learning control system," IEEE Cont. Sys, vol. 10, no. 4, pp. 18-23, April 1990.
12. B. A. Pearlmutter, "Fast exact multiplication by the Hessian," Neural Computation, vol. 6, no. 1, pp. 147-160, 1994.
13. 3) time complexity learning algorithm for fully recurrent continually running networks," Neural Computation, vol. 4, pp. 243-248, 1992.
14. N. Schraudolph, J. Yu, and D. Aberdeen, "Fast online policy gradient learning with smd gain vector, adaptation," in Advances in Neural Information Processing Systems 18, Y. Weiss. B. Schölkopf, and J. Platt, Eds. Cambridge,' MA: MIT Press, 2006, pp. 1185-1192.
15. N. N. Schraudolph, "Local gain adaptation in stochastic gradient descent," Tech. Rep. IDSIA-09-99, Aug 1999.
16. N. N. Schraudolph, J. Yu, and D. Aberdeen, "Fast online policy gradient learning with SMD gain vector adaptation," 19th Annual Conference on Neural Information Processing Systems, Dec 2005, Vancouver, Canada
17. G -Z. Sun, H.-H. Chen, and Y-C. Lee, "Green's (unction method for fast on-line learning algorithm of recurrent neural networks." in NIPS, 1991, pp. 333-340.
18. T. tollenaere, "Supersab: fast adaptive backpropagation with good scaling properties," Neural Networks, vol. 3, no. 5, pp. 561-573, 1990.
19. R. J. Williams and D. Zipser, "A learning algorithm for continually running fully recurrent neural networks," Neural Computation, no. 1, pp. 270-280, 1989.
20. D. Zipser. "A subgrouping strategy that reduces complexity and speeds up learning in recurrent networks," Neural Computation, no. 1, pp. 552-558, 1989.