Greedy linear value-approximation fo radtored Markov decision processes

Proceedings of the National Conference on Artificial Intelligence

Volumn , Issue , 2002, Pages 285-291

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

^a UNIVERSITY OF WATERLOO   (Canada)

^b UNIVERSITY OF TORONTO   (Canada)

^c STANFORD UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; AUTOMATION; DECISION THEORY; ITERATIVE METHODS; LINEAR PROGRAMMING;

MARKOV DECISION PROCESSES (MDP);

MARKOV PROCESSES;

EID: 0036927202     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. Bertsekas, D., and Tsitsiklis, J. 1996. Neuro-Dynamic Programming. Athena Scientific.
2. Bertsekas, D. 1995a. Dynamic Programming and Optimal Control, volume 2. Athena Scientific.
3. Bertsekas, D. 1995b. Nonlinear Optimization. Athena Scientific.
4. Boutilier, C.; Dean, T.; and Hanks, S. 1999. Decision-theoretic planning: Structural assumptions and computational leverage. JAIR 11:1-94.
5. Boutilier, C.; Dearden, R.; and Goldszmidt, M. 2000. Stochastic dynamic programming with factored representations. Artificial Intelligence.
6. de Farias, D., and Van Roy, B. 2001. The linear programming approach to approximate dynamic programming.
7. Dietterich, T. 2000. Hierarchical reinforcement learning with the MAXQ value function decomposition. JAIR 13:227-303.
8. Guestrin, C.; Koller, D.; and Parr, R. 2001a. Max-norm projection for factored MDPs. In Proceedings IJCAI.
9. Guestrin, C.; Koller, D.; and Parr, R. 2001b. Multiagent planning with factored MDPs. In Proceedings NIPS.
10. Koller, D., and Parr, R. 1999. Computing factored value functions for policies in structured MDPs. In Proceedings IJCAI.
11. Koller, D., and Parr, R. 2000. Policy iteration for factored MDPs. In Proceedings UAI.
12. Lusena, C.; Goldsmith, J.; and Mundhenk, M. 2001. Non-approximability results for partially observable Markov decision processes. JAIR 14:83-103.
13. Mundhenk, M.; Goldsmith, J.; Lusena, C.; and Allender, E. 2000. Complexity of finite-horizon Markov decision processes. JACM 47(4):681-720.
14. Puterman, M. 1994. Markov Decision Processes: Discrete Dynamic Programming. Wiley.
15. Sallans, B., and Hinton, G. 2000. Using free energies to represent Q-values in a multiagent reinforcement learning task. In Proceedings NIPS.
16. Schuurmans, D., and Patrascu, R. 2001. Direct value-approximation for factored MDPs. In Proceedings NIPS.
17. Schweitzer, P., and Seidman, A. 1985. Generalized polynomial approximations in Markovian decision problems. J. Math. Anal. and Appl. 110:568-582.
18. Trick, M. A., and Zin, S. E. 1997. Spline approximations to value functions: A linear programming approach. Macroeconomic Dynamics 1:255-277.
19. Williams, R., and Baird, L. 1993. Tight performance bounds on greedy policies based on imperfect value functions. Technical report, Northeastern University.