Symbol acquisition for task-level planning
Name
Lozano-Perez_Symbol acquisition.pdf
Size
212.16 KB
Format
Adobe PDF
Checksum (MD5)
65e76625ca3e10da3bbf70400bf092aa
Author(s)
Konidaris, George
Kaelbling, Leslie P.
Lozano-Perez, Tomas
Date Issued
June 2013
Journal
Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence
Publisher
American Association for the Advancement of Science (AAAS)
Citation
KONIDARIS, G.; KAELBLING, L.; LOZANO-PEREZ, T. Symbol Acquisition for Task-Level Planning. AAAI Workshops, North America, jun. 2013.
Version
Author's final manuscript
Abstract
We consider the problem of how to plan efficiently in low-level, continuous state spaces with temporally abstract actions (or skills), by constructing abstract representations of the problem suitable for task-level planning.The central question this effort poses is which abstract representations are required to express and evaluate plans composed of sequences of skills. We show that classifiers can be used as a symbolic representation system, and that the ability to represent the preconditions and effects of an agent's skills is both necessary and sufficient for task-level planning.The resulting representations allow a reinforcement learning agent to acquire a symbolic representation appropriate for planning from experience.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://www.aaai.org/ocs/index.php/WS/AAAIW13/paper/view/7147
