Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems
Name
wang-icra17.pdf
Description
Accepted version
Size
1.79 MB
Format
Adobe PDF
Checksum (MD5)
fca45bdad56e0744ad24dfa417c3aed4
Author(s)
Wang, Zi
Jegelka, Stefanie
Kaelbling, Leslie Pack
Lozano-Perez, Tomas
Date Issued
May 2017
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Wang, Zi, Jegelka, Stefanie, Kaelbling, Leslie Pack and Lozano-Perez, Tomas. 2017. "Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems."
Version
Author's final manuscript
Abstract
© 2017 IEEE. We introduce a framework for model learning and planning in stochastic domains with continuous state and action spaces and non-Gaussian transition models. It is efficient because (1) local models are estimated only when the planner requires them; (2) the planner focuses on the most relevant states to the current planning problem; and (3) the planner focuses on the most informative and/or high-value actions. Our theoretical analysis shows the validity and asymptotic optimality of the proposed approach. Empirically, we demonstrate the effectiveness of our algorithm on a simulated multi-modal pushing problem.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/icra.2017.7989433
