Piecewise linear value function approximation for factored MDPs

Proceedings of the National Conference on Artificial Intelligence

Volumn , Issue , 2002, Pages 292-299

  Poupart, Pascal ^a   Boutilier, Craig ^a   Patrascu, Relu ^b   Schuurmans, Dale ^b  

^a UNIVERSITY OF TORONTO   (Canada)

^b UNIVERSITY OF WATERLOO   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; DECISION THEORY; OPTIMAL CONTROL SYSTEMS; PIECEWISE LINEAR TECHNIQUES; TREES (MATHEMATICS);

DECISION TREES;

MARKOV PROCESSES;

EID: 0036923210     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. D. P. Bertsekas and J. N. Tsitsiklis. Neuro-dynamic Programming. Athena, Belmont, MA, 1996.
2. C. Boutilier, R. I. Brafman, and C. Geib. Prioritized goal decomposition of Markov decision processes: Toward a synthesis of classical and decision theoretic planning. In Proc. Fifteenth International Joint Conf. on AI, pp.1156-1162, Nagoya, 1997.
3. C. Boutilier, R. Dearden, and M. Goldszmidt. Exploiting structure in policy construction. In Proc. Fourteenth International Joint Conf. on AI, pp.1104-1111, Montreal, 1995.
4. D. Chapman and L. P. Kaelbling. Input generalization in delayed reinforcement learning: An algorithm and performance comparisons. In Proc. Twelfth International Joint Conf. on AI, pp.726-731, Sydney, 1991.
5. T. Dean, R. Givan, and S. Leach. Model reduction techniques for computing approximately optimal solutions for Markov decision processes. In Proc. Thirteenth Conf. on Uncertainty in AI, pp.124-131, Providence, RI, 1997.
6. T. Dean and K. Kanazawa. A model for reasoning about persistence and causation. Comput. Intel, 5(3): 142-150, 1989.
7. R. Dearden and C. Boutilier. Abstraction and approximate decision theoretic planning. Artif. Intel, 89:219-283, 1997.
8. C. Guestrin, D. Koller, and R. Parr. Max-norm projections for factored MDPs. In Proc. Seventeenth International Joint Conf. on AI, pp.673-680, Seattle, 2001.
9. C. Guestrin, D. Koller, and R. Parr. Multiagent planning with factored MDPs. In Advances in Neural Info. Processing Sys. 14 (NIPS-2001), Vancouver, 2001.
10. J. Hoey, R. St-Aubin, A. Hu, and C. Boutilier. SPUDD: Stochastic planning using decision diagrams. In Proc. Fifteenth Conf. on Uncertainty in AI, pp.279-288, Stockholm, 1999.
11. R. A. Howard. Dynamic Programming and Markov Processes. MIT Press, Cambridge, 1960.
12. N. Meuleau, M. Hauskrecht, K. Kim, L. Peshkin, L. P. Kaelbling, T. Dean, and C. Boutilier. Solving very large weakly coupled Markov decision processes. In Proc. Fifteenth National Conf. on AI, pp.165-172, Madison, WI, 1998.
13. A. W. Moore and C. G. Atkeson. The parti-game algorithm for variable resolution reinforcement learning in multidimensional state spaces. Mach. Learn., 21:199-234, 1995.
14. P. Poupart, C. Boutilier, R. Patrascu, and D. Schuurmans. Piecewise linear value function approximation for factored MDPs. In Proc. Eighteenth National Conf. on AI, Edmonton, 2002. to appear.
15. M. L. Puterman. Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, New York, 1994.
16. D. Schuurmans and R. Patrascu. Direct value approximation for factored MDPs. In Advances in Neural Info. Processing Sys. 14 (NIPS-2001), Vancouver, 2001.
17. S. P. Singh and D. Cohn. How to dynamically merge Markov decision processes. In Advances in Neural Info. Processing Sys. 10, pp.1057-1063. MIT Press, Cambridge, 1998.
18. J. Tsitsiklis and B. Van Roy. Feature-based methods for large scale dynamic programming. Mach. Learn., 22:59-94, 1996.