skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning

The Journal of artificial intelligence research, 2018-01, Vol.61, p.215-289 [Peer Reviewed Journal]

2018. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the associated terms available at https://www.jair.org/index.php/jair/about ;ISSN: 1076-9757 ;EISSN: 1943-5037 ;DOI: 10.1613/jair.5575

Full text available

Citations Cited by
  • Title:
    From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning
  • Author: Konidaris, George ; Kaelbling, Leslie Pack ; Lozano-Perez, Tomas
  • Subjects: Computer & video games ; Concrete construction ; Domains ; Learning ; Planning ; Representations ; Statistical analysis
  • Is Part Of: The Journal of artificial intelligence research, 2018-01, Vol.61, p.215-289
  • Description: We consider the problem of constructing abstract representations for planning in high-dimensional, continuous environments. We assume an agent equipped with a collection of high-level actions, and construct representations provably capable of evaluating plans composed of sequences of those actions. We first consider the deterministic planning case, and show that the relevant computation involves set operations performed over sets of states. We define the specific collection of sets that is necessary and sufficient for planning, and use them to construct a grounded abstract symbolic representation that is provably suitable for deterministic planning. The resulting representation can be expressed in PDDL, a canonical high-level planning domain language; we construct such a representation for the Playroom domain and solve it in milliseconds using an off-the-shelf planner. We then consider probabilistic planning, which we show requires generalizing from sets of states to distributions over states. We identify the specific distributions required for planning, and use them to construct a grounded abstract symbolic representation that correctly estimates the expected reward and probability of success of any plan. In addition, we show that learning the relevant probability distributions corresponds to specific instances of probabilistic density estimation and probabilistic classification. We construct an agent that autonomously learns the correct abstract representation of a computer game domain, and rapidly solves it. Finally, we apply these techniques to create a physical robot system that autonomously learns its own symbolic representation of a mobile manipulation task directly from sensorimotor data---point clouds, map locations, and joint angles---and then plans using that representation. Together, these results establish a principled link between high-level actions and abstract representations, a concrete theoretical foundation for constructing abstract representations with provable properties, and a practical mechanism for autonomously learning abstract high-level representations.
  • Publisher: San Francisco: AI Access Foundation
  • Language: English
  • Identifier: ISSN: 1076-9757
    EISSN: 1943-5037
    DOI: 10.1613/jair.5575
  • Source: Alma/SFX Local Collection
    Free E Journals
    ProQuest Central
    DOAJ Directory of Open Access Journals
    American Association for Artificial Intelligence publications
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait