Solving POMDPs: RTDP-Bel vs. point-based algorithms

IJCAI International Joint Conference on Artificial Intelligence

Volumn , Issue , 2009, Pages 1641-1646

  Bonet, Blai ^a   Geffner, Héctor ^b  

^a UNIVERSIDAD SIMÓN BOLÍVAR   (Venezuela)

^b UNIVERSITAT POMPEU FABRA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE;

APPROXIMATE METHODS; DISCRETIZATIONS; POINT-BASED ALGORITHM; REPRESENTATIONAL GAP; TABULAR REPRESENTATIONS; VALUE FUNCTIONS; VALUE ITERATION;

ITERATIVE METHODS;

EID: 78751689703     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. K. Astrom. Optimal control of Markov Decision Processes with incomplete state estimation. J. Math. Anal. Appl., 10:174-205, 1965.
2. A. Barto, S. Bradtke, and S. Singh. Learning to act using real-time dynamic programming. Art. Int., 72:81-138, 1995.
3. D. Bertsekas and J. Tsitsiklis. Neuro-Dynamic Programming. Athena Scientific, 1996.
4. D. Bertsekas. Dynamic Programming and Optimal Control, (2 Vols). Athena Scientific, 1995.
5. B. Bonet and H. Geffner. Learning sorting and decision trees with POMDPs. In Proc. ICML, pages 73-81, 1998.
6. B. Bonet and H. Geffner. Solving large POMDPs using real time dynamic programming. In Proc. AAAI Fall Symp. on POMDPs. AAAI Press, 1998.
7. B. Bonet and H. Geffner. Planning with incomplete information as heuristic search in belief space. In Proc. ICAPS, pages 52-61, 2000.
8. B. Bonet. An ε-optimal grid-based algorithm for Partially Observable Markov Decision Processes. In Proc. ICML, pages 51-58, 2002.
9. M. Hauskrecht. Value-function approximations for partially observable Markov decision processes. JAIR, 13:33-94, 2000. (Pubitemid 33682083)
10. L. P. Kaelbling, M. Littman, and A. R. Cassandra. Planning and acting in partially observable stochastic domains. Art. Int., 101:99-134, 1999.
11. R. Korf. Real-time heuristic search. Art. Int., 42(2-3):189-211, 1990.
12. G. Monahan. A survey of partially observable Markov decision processes: Theory, models and algorithms. Management Science, 28(1):1-16, 1983.
13. J. Pineau, G. J. Gordon, and S. Thrun. Anytime point-based approximations for large POMDPs. JAIR, 27:335-380, 2006.
14. G. Shani, R. I. Brafman, and S. E. Shimony. Forward search value iteration for POMDPs. In Proc. IJCAI, pages 2619-2624, 2007.
15. T. Smith and R. Simmons. Point-based POMDP algorithms: Improved analysis and implementation. In Proc. UAI, pages 542-547, 2005.
16. E. Sondik. The Optimal Control of Partially Observable Markov Decision Processes. PhD thesis, Stanford University, 1971.
17. E. Sondik. The optimal control of partially observable Markov decision processes over the infinite horizon: discounted costs. Oper. Res., 26(2), 1978.
18. M. T. J. Spaan and N. A. Vlassis. Perseus: Randomized point-based value iteration for POMDPs. JAIR, 24:195-220, 2005.
19. R. Sutton and A. Barto. Reinforcement Learning: An Introduction. MIT Press, 1998.