Basis function construction in reinforcement learning using cascade-correlation learning architecture

Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

Volumn , Issue , 2008, Pages 75-82

  Girgin, Sertan ^a   Preux, Philippe ^b  

^a INRIA   (France)

^b UNIV LILLE   (France)

Author keywords

[No Author keywords available]

Indexed keywords

BASIS FUNCTIONS; BENCH-MARK PROBLEMS; INPUT DATUM; LEARNING ARCHITECTURES; LEAST SQUARES POLICY ITERATIONS; NEW APPROACHES; PROBLEM COMPLEXITY; VALUE FUNCTIONS;

APPROXIMATION ALGORITHMS; BENCHMARKING; CURVE FITTING; LEAST SQUARES APPROXIMATIONS; REINFORCEMENT; REINFORCEMENT LEARNING; ROBOT LEARNING;

EDUCATION;

EID: 60649120535     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICMLA.2008.24     Document Type: Conference Paper

References (15)

1. R. Coulom. Reinforcement Learning Using Neural Networks with Applications to Motor Control. PhD thesis, Institut National Polytechnique de Grenoble, 2002.
2. S. E. Fahlman and C. Lebiere. The cascade-correlation learning architecture. In D. S. Touretzky, editor, Advances in NIPS, volume 2, pages 524-532. Morgan Kaufmann, 1990.
3. th European Workshop on Reinforcement Learning, June 2008.
4. S. Girgin and P. Preux. Feature discovery in reinforcement learning using genetic programming. In Proc. of Euro-GP, pages 218-229. Springer-Verlag, Mar. 2008.
5. J. Johns and S. Mahadevan. Constructing basis functions from directed graphs for value function approximation. In ICML, pages 385-392, NY, USA, 2007. ACM.
6. P. W. Keller, S. Mannor, and D. Precup. Automatic basis function construction for approximate dynamic programming and reinforcement learning. In ICML, pages 449-456, NY, USA, 2006. ACM.
7. M. G. Lagoudakis and R. Parr. Least-squares policy iteration. J. of Machine Learning Research, 4:1107-1149, 2003.
8. M. Loth, M. Davy, and P. Preux. Sparse temporal difference learning using LASSO. In Proc. of the IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, Apr. 2007.
9. S. Mahadevan and M. Maggioni. Proto-value functions: A laplacian framework for learning representation and control in markov decision processes. J. of Machine Learning Research, 8:2169-2231, 2007.
10. I. Menache, S. Mannor, and N. Shimkin. Basis function adaptation in temporal difference reinforcement learning. Annals of Operations Research, 134:215-238 (24), 2005.
11. R. Parr, C. Painter-Wakefield, L. Li, and M. Littman. Analyzing feature generation for value-function approximation. In ICML, pages 737-744, NY, USA, 2007. ACM.
12. M. Puterman. Markov Decision Processes - Discrete Stochastic Dynamic Programming. Probability and mathematical statistics. Wiley, 1994.
13. M. Riedmiller and H. Braun. A direct adaptive method for faster backpropagation learning: the rprop algorithm. pages 586-591 Vol. 1, 1993.
14. F. Rivest and D. Precup. Combining td-learning with cascade-correlation networks. In T. Fawcett and N. Mishra, editors, ICML, pages 632-639. AAAI Press, 2003.
15. R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA, 1998. A Bradford Book.