Finite-sample analysis of LSTD

ICML 2010 - Proceedings, 27th International Conference on Machine Learning

Volumn , Issue , 2010, Pages 615-622

  Lazaric, Alessandro ^a   Ghavamzadeh, Mohammad ^a   Munos, Rémi ^a  

^a INRIA   (France)

Author keywords

[No Author keywords available]

Indexed keywords

GENERALIZATION BOUND; LEAST SQUARE; MARKOV CHAIN; POLICY EVALUATION; SAMPLE ANALYSIS; STATIONARY DISTRIBUTION; VALUE FUNCTIONS;

LEARNING SYSTEMS; MARKOV PROCESSES;

LEARNING ALGORITHMS;

EID: 77956549349     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. Antos, A., Szepesvári, Cs., and Munos, R. Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path. Machine Learning Journal, 71:89-129, 2008.
2. Bertsekas, D. Dynamic Programming and Optimal Control. Athena Scientific, 2001.
3. Boyan, J. Least-squares temporal difference learning. Proceedings of the 16th International Conference on Machine Learning, pp. 49-56, 1999.
4. Bradtke, S. and Barto, A. Linear least-squares algorithms for temporal difference learning. Machine Learning, 22:33-57, 1996.
5. Lagoudakis, M. and Parr, R. Least-squares policy iteration. Journal of Machine Learning Research, 4: 1107-1149, 2003.
6. Lazaric, A., Ghavamzadeh, M., and Munos, R. Finite- sample analysis of LSTD. Technical Report inria- 00482189, INRIA, 2010.
7. Sutton, R. and Barto, A. Reinforcement Learning: An Introduction. MIP Press, 1998.
8. Tsitsiklis, J. and Van Roy, B. An analysis of temporal difference learning with function approximation. IEEE Transactions on Automatic Control, 42:674- 690, 1997.