A Dantzig selector approach to temporal difference learning

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 2, Issue , 2012, Pages 1399-1406

  Geist, Matthieu ^a   Scherrer, Bruno ^b   Lazaric, Alessandro ^b   Ghavamzadeh, Mohammad ^b  

^a UMI Georgia Tech CNRS 2958   (France)

^b INRIA   (France)

Author keywords

[No Author keywords available]

Indexed keywords

DANTZIG SELECTOR; FIXED-POINT PROBLEM; HIGH-DIMENSIONAL PROBLEMS; NOVEL ALGORITHM; NUMBER OF SAMPLES; P-MATRIX; REGRESSION ALGORITHMS; REGULARIZATION METHODS; TEMPORAL DIFFERENCE LEARNING; VALUE FUNCTION APPROXIMATION;

LEARNING SYSTEMS;

APPROXIMATION ALGORITHMS;

EID: 84867137477     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. Bickel, P. J., Ritov, Y., and Tsybakov, A. B. Simultaneous analysis of Lasso and Dantzig selector. The Annals of Statistics, 37(4):1705-1732, 2009.
2. Bradtke, S. J. and Barto, A. G. Linear Least-Squares algorithms for temporal difference learning. Machine Learning, 22:33-57, 1996.
3. Candes, E. and Tao, T. The Dantzig selector: statistical estimation when p is much larger than n. Annals of Statistics, 35(6):2313-2351, 2007.
4. Efron, B., Hastie, T., Johnstone, I., and Tibshirani, R. Least Angle Regression. Annals of Statistics, 32(2):407-499, 2004.
5. Farahmand, A., Ghavamzadeh, M., Szepesvári, C., and Mannor, S. Regularized Policy Iteration. In Proc. of NIPS 21, 2008.
6. Farahmand, A. M. and Szepesvári, C. Model selection in reinforcement learning. Machine Learning Journal, 85 (3):299-332, 2011.
7. 1-penalized projected Bellman residual. In Proc. of EWRL 9, 2011.
8. Ghavamzadeh, M., Lazaric, A., Munos, R., and Hoffman, M. Finite-Sample Analysis of Lasso-TD. In Proc. of ICML, 2011.
9. 1 penalization. In Proc. of EWRL 9, 2011.
10. Johns, J., Painter-Wakefield, C., and Parr, R. Linear Complementarity for Regularized Policy Evaluation and Improvement. In Proc. of NIPS 23, 2010.
11. Kolter, J. Z. and Ng, A. Y. Regularization and Feature Selection in Least-Squares Temporal Difference Learning. In Proc. of ICML, 2009.
12. 1-penalized linear estimation with applications. Master's thesis, University of Alberta, 2011.
13. 1-magic matlab library. http://users.ece. gatech.edu/~justin/l1magic/, 2005.
14. Sutton, R. S. and Barto, A. G. Reinforcement Learning: an Introduction. The MIT Press, 1998.
15. Tibshirani, R. Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society, 58(1): 267-288, 1996.
16. Yu, H. and Bertsekas, D. P. Error Bounds for Approximations from Projected Linear Equations. Mathematics of Operations Research, 35:306-329, 2010.