Closing the gap: Improved bounds on optimal POMDP solutions

ICAPS 2011 - Proceedings of the 21st International Conference on Automated Planning and Scheduling

Volumn , Issue , 2011, Pages 194-201

  Poupart, Pascal ^a   Kim, Kee Eung ^b   Kim, Dongho ^b  

^a UNIVERSITY OF WATERLOO   (Canada)

^b Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

BENCH-MARK PROBLEMS; BREADTH-FIRST SEARCH; GRID-BASED APPROACH; LOWER BOUNDS; OPTIMAL VALUE FUNCTIONS; POINT-BASED; POLICY ITERATION; UPPER AND LOWER BOUNDS; UPPER BOUND;

OPTIMAL SYSTEMS; REFINING;

OPTIMIZATION;

EID: 80054839608     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. Brafman, R. I. 1997. A heuristic variable grid solution method for pomdps. In AAAI, 727-733.
2. Guestrin, C.; Koller, D.; Parr, R.; and Venkataraman, S. 2003, Efficient solution algorithms for factored MDPs. Journal of Artificial Intelligence Research 19:399-468. (Pubitemid 41525926)
3. Hauskrecht, M. 1997. Incremental methods for computing bounds in partially observable Markov decision processes, In AAAI, 734-739.
4. Hauskrecht, M. 2000. Value-function approximations for partially observable Markov decision processes. Journal of Artificial Intelligence Research 13:33-94. (Pubitemid 33682083)
5. Hoey, J.; Poupart, P.; von Bertoldi, A.; Craig, T.; Boutilier, C.; and Mihailidis, A. 2010. Automated handwashing assistance for persons with dementia using video and a partially observable Markov decision process. Computer Vision and Image Understanding 114(5):503-519.
6. Kurniawati, H.; Hsu, D.; and Lee, W. 2008. SARSOP: Efficient point-based POMDP planning by approximating optimally reachable belief spaces. In Proc. Robotics: Science and Systems.
7. Lovejoy, W. S. 1991. Computationally feasible bounds for partially observed markov decision processes. Oper. Res. 39:162-175.
8. Papadimitriou, C., and Tsitsiklis, J. N. 1987. The complexity of Markov decision processes. Math. Oper. Res. 12:441-450.
9. Pineau, J.; Gordon, G. J.; and Thrun, S. 2006. Anytime point-based approximations for large POMDPs. Journal of Artificial Intelligence Research 27:335-380.
10. Ross, S.; Pineau, J.; Paquet, S.; and Chaib-draa, B. 2008. Online planning algorithms for POMDPs. Journal of Artificial Intelligence Research 32:663-704.
11. Schuurmans, D., and Patrascu, R. 2001. Direct value-approximation for factored MDPs. In NIPS, 1579-1586.
12. Shani, G.; Brafman, R. I.; and Shimony, S. E. 2007. Forward search value iteration for POMDPs. In IJCAI, 2619-2624.
13. Smallwood, R. D., and Sondik, E. J. 1973. The optimal control of partially observable Markov processes over a finite horizon. Operations Research 21:1071-1088.
14. Smith, T., and Simmons, R. G. 2005. Point-based POMDP algorithms: Improved analysis and implementation. In UAI, 542-547.
15. Spaan, M. T. J., and Vlassis, N. A. 2005. Perseus: Randomized point-based value iteration for POMDPs. Journal of Artificial Intelligence Research 24:195-220. (Pubitemid 43130936)
16. Thomson, B., and Young, S. 2010. Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems. Computer Speech & Language 24(4):562-588.
17. Zhou, R., and Hansen, E. A. 2001. An improved grid-based approximation algorithm for pomdps. In IJCAI, 707-716.