The Complexity of Model Aggregation

Proceedings of the 5th International Conference on Artificial Intelligence Planning Systems, AIPS 2000

Volumn , Issue , 2000, Pages 122-129

  Goldsmith, Judy ^a   Sloan, Robert H ^b  

^a UNIVERSITY OF KENTUCKY   (United States)

^b UNIVERSITY OF ILLINOIS AT CHICAGO   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE;

EXISTENCE PROBLEMS; MARKOV DECISION PROCESSES; MODEL AGGREGATIONS; STATE-SPACE; VALUE ITERATION;

MARKOV PROCESSES;

EID: 0038256821     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (33)

1. Bellman. R. 1957. Dynamic. Programming. Princeton University Press.
2. Blythe, J. 1999. Decision-theoretic planning. AI Magazine 20(2):37 54.
3. Boutilier, C. and Dearden, R. 199G. Approximating value trees in struct unni dynamic programming. In Thirteenth International Conference on Machine Learning, 54 02.
4. Iioutilier. C., Dean, T.; and Hanks, S. 1999. Dccisiontheoretic planning: Structural assumptions and computational leverage. Journal of AI Pcsearch 11:1 94.
5. Boutilier, C; Dearden, R.; and Goldszniidt, M. 1995. Exploiting structure in policy construction. In 14th International Confe.mice. on AI.
6. Boutilier. C: Dearden, H..: and Goldszmidt, M. 1999. Stochastic dynamic programming with factored representations, http://www.es.toronto.edu/~cebly/papers.html.
7. Dean, T ., and Givan. R. 1997. Model minimi/at ion in Markov decision processes. In Proceedings of the 13th National Conference, on Artificial Intelligence and 9th Innovative Applications of Artificial Intelligence Conference (AAA1-97/IAAI-97), 100 111. Menh. Park: A A AT Press.
8. Dean. T.; Givan. R.; and Leach. S. 1997. Model reduction techniques for computing approximately optimal solutions for Markov decision processes. In Geiger, D., and Shcnoy, P. P.. eds.. Pivceedings of the. Pith Conference, on Uncertainty in Artificial Intelligent:!. ((AI-97). 124 131. San Francisco: Morgan Kaufmann Publishers.
9. Fenner, S.; Homer, S.; Green, F .; and Pruim, R. Quantum NP is hard for P H. In Sixth Italian Conference on Theoretical Computer Science. World-Scientific. Feiiner, S.; Homer. S.; Green, F .; and Pruim, R. 1999. Quantum NP is hard for P H. Royal Society of London A 455:3953 3966.
10. Givan. R., and Dean. T. 1997. Model minimization, regression and propositional S T R I P S planning. In Pivceedinys of the. 15th International Joint Conference on Artificial Intelligence (IJCA1-97). 11G3 11GS. San Francisco: Morgan Kaufmann Publishers.
11. Givan, I I. L., and Dean, T. 1999. Model minimization for Markov decision processes. Manuscript.
12. Givan, 11.; Leach. S.; and Dean, T. 1997. Bounded parameter Markov decision processes. In Steel, S., and fennec on Planning (ECP-97): Recent Advances in AI Planning, volume 1348 of LNAI, 234-246. Berlin: Springer.
13. Givan, R. 1999. Personal communication.
14. Goldsmith, J ., and Mundhenk, M. 1998. Complexity issues in Markov decision processes. In Pioceedings of IEEE Conference on Computational Complexity. 272 280.
15. Goldsmith, J .; Littman, M.; and Mundhenk, M. 1997. The complexity of plan existence and evaluation in probabilistic domains. In Proc. 13th Conf. on Uncertainty in AI. Morgan Kaufmann Publishers.
16. Harmanec, D. 1999. A generalization of the concept of Markov decision process to imprecise probabilities. In Proceedings of the 1st Internation Symposium on Imprecise Probabilities and Their Applications, 175 182.
17. Hoey. J .; St-Aubin, R.; Hu, A.; and Boutilier. C. 1999. SPUDD: Stochastic planning using decision diagrams. In Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligemx, 279-288.
18. Littman, M.; Goldsmith, J .; and Mundhenk, M. 1998. The computational complexity of probabilistic plan existence and evaluation. The Journal of AI Research 9:1-36.
19. Littman, M. L.; Majercik, S. M.; and Pitassi, T. 2000. Stochastic Boolean satisfiability. Journal of Automated Reasoning.
20. Littman, M. 1997. Probabilistic prepositional planning: Representations and complexity. In Proc. 14th National Conference on A I. A A Al Press / M I T Press.
21. Littman, M. L. 1999. Initial experiments in stochastic satisfiability. In Proceedings of Sixteenth National Conference on Artificial Intelligence.
22. Lusena, C; Goldsmith, J .; and Mundhenk, M. 1999. Xonapproximability results for Markov decision processes. In preparation.
23. Majercik, M., and Littman, M. 1998a. Maxplan: A new approach to probabilistic planning. In AHificial Intelligence and Planning Systems, 86- 93.
24. Majercik, S. M., and Littman, M. L. 1998b. Using caching to solve larger probabilistic planning problems. In Proceedings of Fifteenth National Conference on Artificial Intelligence, 954-959.
25. Mundhenk, M.; Goldsmith, J .; Lusena, C.; and Allender, E. 1999. Complexity results for finite-horizon Markov decision process. Journal of the ACM. To Appear.
26. Papadimitriou, C. 1994. Computational Complexity. Addison-Wesley.
27. Puterman, M. L ., and Shin, M. 1978. Modified policy iteration algorithms for discounted Markov decision problems. Management Science 24:1127- 1137.
28. Toda, S. 1991. PP is as hard as the polynomial-time hierarchy. SIAM Journal on Computing 20:865-877.
29. Torán, J. 1988. Structural Properties of the. Counting Hierarchies. Ph.D. Dissertation, Facultat. d'Informàtica de Barcelona.
30. Torán, J. 1991. Complexity classes defined by counting quantifiers. Journal of the ACM 38(3):753-774.
31. Torán. J. 1999. Personal communication.
32. Tsitsiklis, J. N., and Roy, B. V. 1996. Feature-based methods for large scale dynamic programming. Machine Learning 22:59-94.
33. Wagner. K. 1986. The complexity of combinatorial problems with succinct, input representation. Acta Informatica 23:325-356.