Reinforcement learning with limited reinforcement: Using bayes risk for active learning in POMDPs

Proceedings of the 25th International Conference on Machine Learning

Volumn , Issue , 2008, Pages 256-263

  Doshi, Finale ^a   Pineau, Joelle ^b   Roy, Nicholas ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^b MCGILL UNIVERSITY   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

EDUCATION; LEARNING SYSTEMS; PLANNING; REINFORCEMENT LEARNING; ROBOT LEARNING;

ACTIVE LEARNINGS; APPROXIMATION APPROACHES; BAYES RISKS; DOMAIN KNOWLEDGES; HIDDEN STATES; MODEL PARAMETERS; PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES; PLANNING DOMAINS; ACTIVE LEARNING; DOMAIN KNOWLEDGE; HIDDEN STATE; PARTIALLY OBSERVABLE MARKOV DECISION PROCESS;

REINFORCEMENT;

EID: 56449086386     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Dearden, R., Friedman, N., & Andre, D. (1999). Model based Bayesian exploration. .
2. Doshi, F., & Roy, N. (2007). Efficient model learning for dialog management. Technical Report SS-07-07. AAA1 Press.
3. Even-Dar, E., Kakade, S. M., & Mansour, Y. (2005). Reinforcement learning in POMDPs without resets. IJCAI.
4. Iaulmes, R., Pineau, J., & Precup, D. (2005). Learning in non-stationary partially observable Markov decision processes. ECML Workshop on Reinforcement Learning in Non-Stationary Environments.
5. Littman, M. L., Cassandra, A. R., & Kaelbling, L. P. (1995). Learning policies for partially observable environments: scaling up. ICML.
6. Millet, I. (1998). The variational Bayesian EM algorithm for incomplete data: with application to scoring graphical model structures. Journal of Multi-Criteria Decision Analysis, 6.
7. Moral, P., Doucet, A., & Peters, G. (2002). Sequential Monte Carlo samplers.
8. Ng, A., & Russell, S. (2000). Algorithms for inverse reinforcement learning. ICML.
9. Pineau, J., Gordon, G., & Thrun, S. (2003). Point-based value iteration: an anytime algorithm for POMDPs. IJCAI.
10. Poupart, P., & Vlassis, N. (2008). Model-based Bayesian reinforcement learning in partially observable domains. ISAIM.
11. Poupart, P., Vlassis, N., Hoey, J., & Regan, K. (2006). An analytic solution to discrete Bayesian reinforcement learning. ICML.
12. Roy, N., Pineau, J., & Thrun, S. (2000). Spoken dialogue management using probabilistic reasoning. ACL. Hong Kong.
13. Sato, M. (1999). Fast learning of on-line EM algorithm. TR-H-281, ATR Human Information Processing Lab.
14. Shani, G., Brafman, R., & Shimony, S. (2007). Forward search value iteration for POMDPs. IJCAI.
15. Srrehl, A. L., Li, L., & Littman, M. L. (2006). Incremental model-based learners with formal learning-time guarantees. UAI.
16. Strens, M. (2000). A Bayesian framework for reinforcement learning. ICML.
17. Watkins, C. (1989). Learning from delayed rewards. Doctoral dissertation, Cambridge University.
18. Williams, J., & Young, S. (2005). Scaling up POMDPs for dialogue management: The "summary POMDP" method. Proceedings of the IEEE ASRU Workshop.