Hierarchical Solution of Large Markov Decision Processes
Name
Kaelbling_Hierarchical solution.pdf
Size
370.41 KB
Format
Adobe PDF
Checksum (MD5)
30ec69d506cfd61c16a1ae63bff47358
Author(s)
Barry, Jennifer
Kaelbling, Leslie P.
Lozano-Perez, Tomas
Date Issued
May 2010
Journal
ICAPS-10 Workshop on Planning and Scheduling Under Uncertainty, 2010
Publisher
Association for the Advancement of Artificial Intelligence
Citation
Barry, Jennifer, Leslie Pack Kaelbling and Tomas Lozano-Perez. "Hierarchical Solution of Large Markov Decision Processes." ICAPS-10 Workshop on Planning and Scheduling Under Uncertainty, Toronto, Canada, May 12-16, 2010.
Version
Author's final manuscript
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Attribution-Noncommercial-Share Alike 3.0 Unported
Persistent DSpace Link
DOI of Published Version
http://digital.cs.usu.edu/~danbryce/icaps10/PSUWS/Accepted_Papers.html
