Modelling transition dynamics in MDPs with RKHS embeddings

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

Volumn 1, Issue , 2012, Pages 535-542

  Grünewälder, Steffen ^a   Lever, Guy ^a   Baldassarre, Luca ^a   Pontil, Massimilano ^a   Gretton, Arthur ^b,c  

^a UNIVERSITY COLLEGE LONDON   (United Kingdom)

^b UNIVERSITY COLLEGE LONDON   (United Kingdom)

^c MAX PLANCK INSTITUTE FOR INTELLIGENT SYSTEMS   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSICAL CONTROL; CONDITIONAL DISTRIBUTION; DYNAMIC PROGRAMMING METHODS; EMBEDDINGS; GAUSSIAN PROCESSES; INNER PRODUCT; LEARNING TASKS; LEAST SQUARE; LINEAR COMPLEXITY; MARKOV DECISION PROCESSES; NAVIGATION PROBLEM; NONPARAMETRIC APPROACHES; OPTIMAL POLICIES; OPTIMISATIONS; POLICY ITERATION; REPRODUCING KERNEL HILBERT SPACES; TRANSITION DYNAMICS; TRANSITION PROBABILITIES; VALUE ESTIMATION; VALUE FUNCTIONS; VALUE ITERATION ALGORITHM;

DYNAMICS; ESTIMATION; EXPERIMENTS; ITERATIVE METHODS; LEARNING ALGORITHMS; LEARNING SYSTEMS; MARKOV PROCESSES;

OPTIMIZATION;

EID: 84867133646     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (29)

1. Bach, F. R. and Jordan, M. I. Kernel independent component analysis. J. Mach. Learn. Res., 3:1-48, 2002.
2. Bertsekas, D. and Shreve, S. Mathematical issues in dynamic programming. 1978. Supplementary material to Stochastic Optimal Control: The Discrete-Time Case, Academic press, 1978.
3. Böhmer, W. Robot Navigation using Reinforcement Learning and Slow Feature Analysis. ArXiv, 2012.
4. Deisenroth, M. P., Rasmussen, C. E., and Peters, J. Gaussian process dynamic programming. Neurocomputing, 72(7-9):1508-1524, 2009.
5. Engel, Y., Mannor, S., and Meir, R. Reinforcement learning with gaussian processes. In ICML, 2005.
6. Granas, A. and Dugundji, J. Fixed Point Theory. Springer-Verlag, 2003.
7. Grünewälder, S., Lever, G., Baldassarre, L., Pontil, M., and Gretton, A. Modelling transition dynamics in mdps with rkhs embeddings. In arXiv, 2012.
8. Kroemer, O. and Peters, J. A non-parametric approach to dynamic programming. In NIPS, 2011.
9. Lagoudakis, M. G. and Parr, R. Least-squares policy iteration. J. Mach. Learn. Res., 4, December 2003.
10. Micchelli, C.A. and Pontil, M. On learning vector-valued functions. Neural Computation, 17(1):177-204, 2005.
11. Ormoneit, D. and Sen, S. Kernel-based reinforcement learning. In Machine Learning, pp. 161-178, 1999.
12. Parr, R., Li, L., Taylor, G., Painter-Wakefield, C., and Littman, M. L. An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning. In ICML, 2008.
13. Petersen, K. B. and Pedersen, M. S. The matrix cookbook, 2008.
14. Rasmussen, C. E. and Kuss, M. Gaussian processes in reinforcement learning. In NIPS. MIT Press, 2003.
15. Reed, M. and Simon, B. Methods of modern mathematical physics. Vol. 1: Functional Analysis. Academic Press, San Diego, 1980.
16. Shawe-Taylor, J. and Cristianini, N. Kernel Methods for Pattern Analysis. Cambridge University Press, 2004.
17. Singh, S. P. and Yee, R. C. An upper bound on the loss from approximate optimal-value functions. Machine Learning, 16(3):227-233, 1994.
18. Smola, A. J. and Kondor, R. I. Kernels and regularization on graphs. In COLT, 2003.
19. Song, L., Huang, J., Smola, A. J., and Fukumizu, K. Hilbert space embeddings of conditional distributions with applications to dynamical systems. In ICML, 2009.
20. Song, L., Boots, B., Siddiqi, S., Gordon, G., and Smola, A. Hilbert space embeddings of hidden Markov models. In ICML, 2010a.
21. Song, L., Gretton, A., and Guestrin, C. Nonparametric tree graphical models. AISTATS, 9, 2010b.
22. Song, L., Gretton, A., Bickson, D., Low, Y., and Guestrin, C. Kernel belief propagation. In AISTATS, 2011.
23. Sriperumbudur, B., Gretton, A., Fukumizu, K., Lanckriet, G., and Schölkopf, B. Hilbert space embeddings and metrics on probability measures. JMLR, 11, 2010.
24. Steinwart, I. and Christmann, A. Support Vector Machines. Springer, 2008.
25. Szepesvari, C. Algorithms for reinforcement learning. Morgan and Claypool, 2009.
26. Taylor, G. and Parr, R. Kernelized value function approximation for reinforcement learning. In ICML, 2009.
27. Wasserman, L. All of Nonparametric Statistics. Springer, 2006.
28. Wendland, H. Scattered Data Approximation. Cambridge University Press, Cambridge, UK, 2005.
29. Xu, X., Xie, T., Hu, D., and Lu, X. Kernel least-squares temporal difference learning. International Journal of Information Technology, 2005.