|
|
|
|
LEADER |
01444 am a22002293u 4500 |
001 |
61387 |
042 |
|
|
|a dc
|
100 |
1 |
0 |
|a Barry, Jennifer
|e author
|
100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
|e contributor
|
100 |
1 |
0 |
|a Kaelbling, Leslie P.
|e contributor
|
100 |
1 |
0 |
|a Barry, Jennifer
|e contributor
|
100 |
1 |
0 |
|a Kaelbling, Leslie P.
|e contributor
|
100 |
1 |
0 |
|a Lozano-Perez, Tomas
|e contributor
|
700 |
1 |
0 |
|a Kaelbling, Leslie P.
|e author
|
700 |
1 |
0 |
|a Lozano-Perez, Tomas
|e author
|
245 |
0 |
0 |
|a Hierarchical Solution of Large Markov Decision Processes
|
260 |
|
|
|b Association for the Advancement of Artificial Intelligence,
|c 2011-03-03T19:04:22Z.
|
856 |
|
|
|z Get fulltext
|u http://hdl.handle.net/1721.1/61387
|
520 |
|
|
|a This paper presents an algorithm for finding approximately optimal policies in very large Markov decision processes by constructing a hierarchical model and then solving it. This strategy sacrifices optimality for the ability to address a large class of very large problems. Our algorithm works efficiently on enumerated-states and factored MDPs by constructing a hierarchical structure that is no larger than both the reduced model of the MDP and the regression tree for the goal in that MDP, and then using that structure to solve for a policy.
|
546 |
|
|
|a en_US
|
655 |
7 |
|
|a Article
|
773 |
|
|
|t ICAPS-10 Workshop on Planning and Scheduling Under Uncertainty, 2010
|