MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Guiding search in continuous state-action spaces by learning an action sampler from off-target search experience

Author(s)
Kaelbling, Leslie P.; Lozano-Pérez, Tomás; Kim, Beomjoon
Thumbnail
DownloadAccepted version (1.828Mb)
Open Access Policy

Open Access Policy

Creative Commons Attribution-Noncommercial-Share Alike

Terms of use
Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/
Metadata
Show full item record
Abstract
Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. In robotics, it is essential to be able to plan efficiently in high-dimensional continuous state-action spaces for long horizons. For such complex planning problems, unguided uniform sampling of actions until a path to a goal is found is hopelessly inefficient, and gradient-based approaches often fall short when the optimization manifold of a given problem is not smooth. In this paper, we present an approach that guides search in continuous spaces for generic planners by learning an action sampler from past search experience. We use a Generative Adversarial Network (GAN) to represent an action sampler, and address an important issue: search experience consists of a relatively large number of actions that are not on a solution path and a relatively small number of actions that actually are on a solution path. We introduce a new technique, based on an importance-ratio estimation method, for using samples from a non-target distribution to make GAN learning more data-efficient. We provide theoretical guarantees and empirical evaluation in three challenging continuous robot planning problems to illustrate the effectiveness of our algorithm.
Date issued
2018
URI
https://hdl.handle.net/1721.1/137707
Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Citation
Kaelbling, Leslie P., Lozano-Pérez, Tomás and Kim, Beomjoon. 2018. "Guiding search in continuous state-action spaces by learning an action sampler from off-target search experience."
Version: Author's final manuscript

Collections
  • MIT Open Access Articles

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.