Computing factored value functions for policies in structured MDPs

IJCAI International Joint Conference on Artificial Intelligence

Volumn 2, Issue , 1999, Pages 1332-1339

  Koller, Daphne ^a   Parr, Ronald ^a  

^a Stanford University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADDITIVE FUNCTION; ADDITIVE VALUE FUNCTIONS; COMPACT REPRESENTATION; DYNAMIC BAYESIAN NETWORKS; LINEAR FUNCTIONS; MARKOV DECISION PROCESSES; PROCESS DESCRIPTIONS; VALUE DETERMINATION;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; MARKOV PROCESSES;

DYNAMIC PROGRAMMING;

EID: 84880688552     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. F. Bacchus and A. Grove. Graphical models for preference and utility. In Proc. UAI, 1995.
2. C. Boutilier and R. Dearden. Approximating value trees in structured dynamic programming. In Proc. ICML, pages 54-62, 1996.
3. C. Boutilier, R.I. Brafman, and C. Geib. Prioritized goal decomposition of Markov decision processes: Towards a synthesis of classical and decision theoretic planning. In Proc. UAI, pages 24-32, 1998.
4. C. Boutilier, T. Dean, and S. Hanks. Decision theoretic planning: Structural assumptions and computational leverage. Journal of Artificial Intelligence Research, 1999.
5. X. Boyen and D. Koller. Tractable inference for complex stochastic processes. In Proc. UAI, 1998.
6. T. Dean, R. Givan, and S. Leach. Model reduction techniques for computing approximately optimal solutions for Markov decision processes. In Proc. UAI, 1997.
7. G J. Gordon. Stable function approximation in dynamic programming. In Proc. ICML, pages 261-268, 1995.
8. R.A. Howard and J.E, Matheson. Influence diagrams. In Readings on the Principles and Applications of Decision Analysis, pages 721-762. Strategic Decisions Group, 1984.
9. R.L. Keeney and H. Raiffa. Decisions with Multiple Objectives: Preferences and Value Tradeoffs. Wiley, 1976.
10. N. Meuleau, M. Hauskrecht, K-E. Kim, L. Peshkin, L.P. Kaelbling, T. Dean, and C. Boutilier. Solving very large weakly coupled Markov decision processes. In Proc. AAA/, pages 165-172, 1998.
11. E. Nelson. The adjoint Markoff process. Duke Mathematical Journal, 25, 1958.
12. S.P. Singh and D. Cohn. How to dynamically merge Markov decision processes. In NIPS 10, pages 1057-1063, 1998.
13. G. Strang. Linear Algebra and Its Applications. Academic Press, 1980.
14. R.S. Sutton, S. Singh, D. Precup, and B. Ravindran. Improved switching among temporally abstract actions. In NIPS 12, 1999. To appear.
15. P. Tadepalli and D. Ok. Scaling up average reward reinforcement learning by approximating the domain models and the value function. In Proc. ICML, 1996.
16. J. D. Tsitsiklis and B. Van Roy. Feature-based methods for large scale dynamic programming. Machine Learning, 22(1):59-94, January 1996. (Pubitemid 126724363)
17. B. Van Roy. Learning and Value Function Approximation in Complex Decision Problems. PhD thesis, Massachusetts Institute of Technology, 1998.