Near-optimal BRL using optimistic local transitions

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

Volumn 1, Issue , 2012, Pages 97-104

  Araya López, Mauricio ^a   Thomas, Vincent ^a   Buffet, Olivier ^a  

^a LORIA   (France)

Author keywords

[No Author keywords available]

Indexed keywords

COMBINATORIAL EXPLOSION; HIGH PROBABILITY; LOCAL TRANSITIONS; SAMPLE COMPLEXITY; TRANSITION FUNCTIONS; UNKNOWN ENVIRONMENTS;

OPTIMIZATION; REINFORCEMENT LEARNING;

HEURISTIC ALGORITHMS;

EID: 84867138336     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Araya-López, M., Thomas, V., and Buffet, O. Near-optimal BRL using optimistic local transitions (extended version). Technical Report 7965, INRIA, May 2012.
2. Asmuth, J., Li, L., Littman, M.L., Nouri, A., and Wingate, D. A Bayesian sampling approach to exploration in reinforcement learning. In Proc. of UAI, 2009.
3. Brafman, R.I. and Tennenholtz, M. R-max - a general polynomial time algorithm for near-optimal reinforcement learning. JMLR, 3:213-231, 2003.
4. Duff, M. Optimal learning: Computational procedures for Bayes-adaptive Markov decision processes. PhD thesis, University of Massachusetts Amherst, 2002.
5. Kearns, M. and Singh, S. Near-optimal reinforcement learning in polynomial time. In Machine Learning, pp. 260-268, 1998.
6. Kolter, J. and Ng, A. Near-Bayesian exploration in polynomial time. In Proc. of ICML, 2009.
7. Poupart, P., Vlassis, N., Hoey, J., and Regan, K. An analytic solution to discrete Bayesian reinforcement learning. In Proc. of ICML, 2006.
8. Puterman, M. Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley-Interscience, 1994.
9. Sorg, J., Singh, S., and Lewis, R. Variance-based rewards for approximate Bayesian reinforcement learning. In Proc. of UAI, 2010.
10. Strehl, A.L., Li, L., and Littman, M.L. Reinforcement learning in finite MDPs: PAC analysis. JMLR, 10: 2413-2444, December 2009.
11. Strens, Malcolm J. A. A Bayesian framework for rein- forcement learning. In Proc. of ICML, 2000.
12. Sutton, R. and Barto, A. Reinforcement Learning: An Introduction. MIT Press, 1998.
13. Szita, Istvn and Szepesvri, Csaba. Model-based reinforcement learning with nearly tight exploration complexity bounds. In Proc. of ICML, 2010.
14. Valiant, L. G. A theory of the learnable. In Proc. of STOC ACM, 1984.
15. Walsh, T.J., Szita, I., Diuk, C., and Littman, M.L. Exploring compact reinforcement-learning representations with linear regression. In Proc. of UAI, 2009.