Reinforcement learning for dialog management using least-squares policy iteration and fast feature selection

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2009, Pages 2475-2478

  Li, Lihong ^a   Williams, Jason D ^b   Balakrishnan, Suhrid ^b  

^a RUTGERS UNIVERSITY   (United States)

^b AT AND T LABS RESEARCH   (United States)

Author keywords

Dialog management; Partially observable Markov decision processes; Spoken dialog systems

Indexed keywords

DIALOG MANAGEMENT; DIALOG SYSTEMS; FEATURE SELECTION; LEAST SQUARE; PARTIALLY OBSERVABLE MARKOV DECISION PROCESS; POLICY ITERATION; SPOKEN DIALOG SYSTEMS;

DECISION MAKING; FEATURE EXTRACTION; HUMAN COMPUTER INTERACTION; MARKOV PROCESSES; REINFORCEMENT; REINFORCEMENT LEARNING; SPEECH COMMUNICATION;

LEARNING ALGORITHMS;

EID: 70450186275     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. E. Levin, R. Pieraccini, and W. Eckert, "A stochastic model of human-machine interaction for learning dialog strategies," IEEE Trans. Speech Audio Process., vol. 8, no. 1, pp. 11-23, 2000.
2. N. Roy, J. Pineau, and S. Thrun, "Spoken dialogue management using probabilistic reasoning," in ACL, 2000, pp. 93-100.
3. J. Henderson, O. Lemon, and K. Georgila, "Hybrid reinforcement/ supervised learning of dialogue policies from fixed data sets," Computational Linguistics, vol. 34, no. 4, pp. 487-511, 2008.
4. B. Thomson, J. Schatzmann, and S. Young, "Bayesian update of dialogue state for robust dialogue systems," in ICASSP, 2008.
5. J. D. Williams, "Integrating expert knowledge into POMDP optimization for spoken dialog systems," in AAAI-08 Workshop on Advancements in POMDP Solvers, 2008.
6. R. Parr, C. Painter-Wakefield, L. Li, and M. L. Littman, "Analyzing feature generation for value-function approximation," in Int. Conf. Mach. Learning, 2007, pp. 737-744.
7. S. Mahadevan and M. Maggioni, "Proto-value functions: A Laplacian framework for learning representation and control in Markov decision processes," Journall of Machine Learning Research, vol. 8, pp. 2169-2231, 2007.
8. M. G. Lagoudakis and R. Parr, "Least-squares policy iteration," Journall of Machine Learning Research, vol. 4, pp. 1107-1149, 2003.
9. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction. MIT Press, 1998.
10. R. S. Sutton, "Learning to predict by the methods of temporal differences," Machine Learning, vol. 3, pp. 9-44, 1988.
11. J. D. Williams, "Demonstration of a POMDP voice dialer," In ACL/HLT, 2008.
12. -, "The best of both worlds: Unifying conventional dialog systems and pomdps," in ICSLP-08, 2008.
13. M. Walker, "An application of reinforcement learning to dialogue strategy selection in a spoken dialogue system for email," Journal of Articial Intelligence Research, vol. 12, pp. 387-416, 2000.
14. V. Rieser and O. Lemon, "Automatic learning and evaluation of user-centered objective functions for dialogue system optimisation," in Proc LREC, Marrakech, 2008.
15. M. Frampton and O. Lemon, "Using dialogue acts to learn better repair strategies for spoken dialogue systems," in Proc ICASSP, Las Vegas, 2008.