Bayesian reinforcement learning for POMDP-based dialogue systems

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2011, Pages 2156-2159

  Png, Shaowei ^a   Pineau, Joelle ^a  

^a MCGILL UNIVERSITY   (Canada)

Author keywords

Bayesian Learning; POMDPs (Partially Observable Markov Decision Processes); Reinforcement Learning; Spoken Dialogue

Indexed keywords

BAYESIAN LEARNING; DIALOGUE SYSTEMS; MODEL PARAMETERS; ON-LINE PLANNING; PARTIALLY OBSERVABLE MARKOV DECISION PROCESS; SCALE-UP; SPEECH RECOGNITION TECHNOLOGY; SPOKEN DIALOGUE; SPOKEN DIALOGUE SYSTEM;

ALGORITHMS; MARKOV PROCESSES; REINFORCEMENT LEARNING; SIGNAL PROCESSING; SPEECH COMMUNICATION; SPEECH PROCESSING;

SPEECH RECOGNITION;

EID: 80051605697     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5946754     Document Type: Conference Paper

References (21)

1. K. Georgila, J. Henderson, and O. Lemon, "User simulation for spoken dialogue systems: Learning and evaluation," in ICSLP, 2006.
2. R. Nisimura, T. Uchida, A. Lee, H. Saruwatari, K. Shikano, and Y. Matsumoto, "ASKA: receptionist robot with speech dialogue system," in ICRA, 2002.
3. A. Atrash and J. Pineau, "A bayesian reinforcement learning approach for customizing human-robot interfaces," in IUI, 2009.
4. S.P. Singh, D.J. Litman, M.J. Kearns, and M.A. Walker, "Optimizing dialogue management with reinforcement learning: Experiments with the NJFun system," JAIR, vol. 16, no. 1, 2002.
5. N. Roy, J. Pineau, and S. Thrun, "Spoken dialogue management using probabilistic reasoning," in ACL, 2000.
6. J.D. Williams, P. Poupart, and S. Young, "Partially observable Markov decision processes with continuous observations for dialogue management," Recent Trends in Discourse and Dialogue, 2008.
7. R. Dearden, N. Friedman, and D. Andre, "Model based Bayesian exploration," in UAI, 1999.
8. P. Poupart, N. Vlassis, J. Hoey, and K. Regan, "An analytic solution to discrete Bayesian reinforcement learning," in ICML, 2006.
9. S. Ross, B. Chaib-draa, and J. Pineau, "Bayes-Adaptive POMDPs," in NIPS, 2007.
10. E.J. Sondik, "The Optimal Control of Partially Observable Markov Processes.," in PhD thesis, Stanford University, 1971.
11. L.P. Kaelbling, M.L. Littman, and A.R. Cassandra, "Planning and acting in partially observable stochastic domains," Artificial Intelligence, vol. 101, no. 1-2, 1998.
12. J. Pineau, G. Gordon, and S. Thrun, "Point-based value iteration: An anytime algorithm for POMDPs," in IJCAI, 2003.
13. T. Smith and R. Simmons, "Heuristic search value iteration for POMDPs," in UAI, 2004.
14. M.T.J. Spaan and N. Vlassis, "A point-based POMDP algorithm for robot planning," in ICRA, 2004.
15. H. Kurniawati, D. Hsu, and W.S. Lee, "SARSOP: Efficient point-based POMDP planning by approximating optimally reachable belief spaces," in RSS, 2008.
16. S. Ong, S. Png, D. Hsu, and W. Lee, "POMDPs for robotic tasks with mixed observability," in RSS, 2009.
17. S. Ross, J. Pineau, S. Paquet, and B. Chaib-Draa, "Online planning algorithms for POMDPs," JAIR, vol. 32, no. 1, 2008.
18. G. Shani, R. Brafman, and S. Shimony, "Model-based online learning of POMDPs," Machine Learning: ECML 2005, pp. 353-364, 2005.
19. D.P. Bertsekas and D.A. Castanon, "Rollout algorithms for stochastic scheduling problems," Journal of Heuristics, vol. 5, no. 1, 1999.
20. S. Paquet, L. Tobin, and B. Chaib-draa, "Real-time decision making for large POMDPs," Advances in Artificial Intelligence, 2005.
21. A. Atrash, R. Kaplow, J. Villemure, R.West, H. Yamani, and J. Pineau., "Development and validation of a robust speech interface for improved human-robot interaction," IJSR, vol. 1, 2009.