Batch-iFDD for representation expansion in large MDPs
Name
Roy_Batch-iFDD.pdf
Size
1.12 MB
Format
Adobe PDF
Checksum (MD5)
711ef94cf645750047ad7e6a3b593c90
Author(s)
Geramifard, Alborz
Walsh, Thomas J.
Roy, Nicholas
How, Jonathan P.
Date Issued
July 2013
Journal
Proceedings of the 2013 Conference on Uncertainty in Artificial Intelligence
Publisher
Association for Uncertainty in Artificial Intelligence (AUAI)
Citation
Geramifard, Alborz, Thomas J. Walsh, Nicholas Roy, and Jonathan P. How. "Batch-iFDD for representation expansion in large MDPs." 2013 Conference on Uncertainty in Artificial Intelligence (July 2013).
Version
Author's final manuscript
Abstract
Matching pursuit (MP) methods are a promising class of feature construction algorithms for value function approximation. Yet existing MP methods require creating a pool of potential features, mandating expert knowledge or enumeration of a large feature pool, both of which hinder scalability. This paper introduces batch incremental feature dependency discovery (Batch-iFDD) as an MP method that inherits a provable convergence property. Additionally, Batch-iFDD does not require a large pool of features, leading to lower computational complexity. Empirical policy evaluation results across three domains with up to one million states highlight the scalability of Batch-iFDD over the previous state of the art MP algorithm.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://auai.org/uai2013/prints/papers/139.pdf
