Approximate linear-programming algorithms for graph-based Markov decision processes

Frontiers in Artificial Intelligence and Applications

Volumn 141, Issue , 2006, Pages 590-594

  Forsell, Nicklas ^a,b   Sabbadin, Régis ^b  

^a SWEDISH UNIVERSITY OF AGRICULTURAL SCIENCES   (Sweden)

^b CEMAGREF   (France)

Author keywords

[No Author keywords available]

Indexed keywords

GRAPHIC METHODS; LINEAR PROGRAMMING;

APPROXIMATE LINEAR PROGRAMMING; APPROXIMATE SOLUTION; COMPACT REPRESENTATION; EXPONENTIALS; GRAPH STRUCTURES; GRAPH-BASED; LINEAR PROGRAMMING ALGORITHM; MARKOV DECISION PROCESSES; METHOD COMPLEXITY; SOLUTION ALGORITHMS;

MARKOV PROCESSES;

EID: 84885992951     PISSN: 09226389     EISSN: 18798314     Source Type: Book Series    
DOI: None     Document Type: Article

References (8)

1. C. Boutilier, R. Dearden, and M. Goldszmidt, 'Stochastic dynamic programming with factored representations', Artificial Intelligence, 121(1), 49-107, (2000).
2. R. K. Chornei, H. Daduna, and P. S. Knopov, 'Controlled markov fields with finite state space on graphs', Stochastic Models, 21, 847-874, (2005).
3. D. P. de Farias and B. Van Roy, 'On constraint sampling in the linear programming approach to approximate dynamic programming', Math. of Op. Research, 29(3), 462-478, (2004).
4. C. Guestrin, D. Koller, R. Parr, and S. Venkataraman, 'Efficient solution algorithms for factored MDPs', Journal of Artificial Intelligence Research, 19, 399-468, (2003).
5. C. E. Guestrin, Planning under uncertainty in complex structured environments, Ph.D. dissertation, Stanford University, 2003.
6. N. Peyrard and R. Sabbadin, 'Mean field approximation of the policy iteration algorithm for graph-based mdp', in Proceedings ECAI'06, (2006).
7. M. L. Puterman, Markov Decision Processes, JohnWiley and Sons, New York, 1994.
8. R. J. Williams and L.C.I. Baird, 'Tight performance bounds on greedy policies based on imperfect value functions', Technical report, College of Computer Science, Northeastern University, Boston, MA, (1993).