Planning in factored state and action spaces with learned Binarized Neural Network transition models

Buser Say, Scott Sanner

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


In this paper, we leverage the efficiency of Binarized Neural Networks (BNNs) to learn complex state transition models of planning domains with discretized factored state and action spaces. In order to directly exploit this transition structure for planning, we present two novel compilations of the learned factored planning problem with BNNs based on reductions to Boolean Satisfiability (FDSAT-Plan) as well as Binary Linear Programming (FD-BLP-Plan). Experimentally, we show the effectiveness of learning complex transition models with BNNs, and test the runtime efficiency of both encodings on the learned factored planning problem. After this initial investigation, we present an incremental constraint generation algorithm based on generalized landmark constraints to improve the planning accuracy of our encodings. Finally, we show how to extend the best performing encoding (FD-BLP-Plan+) beyond goals to handle factored planning problems with rewards.
Original languageEnglish
Title of host publicationProceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
EditorsJérôme Lang
Place of PublicationMarina del Rey CA USA
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Number of pages7
ISBN (Electronic)9780999241127
Publication statusPublished - 2018
Externally publishedYes
EventInternational Joint Conference on Artificial Intelligence 2018 - Stockholm, Sweden
Duration: 13 Jul 201819 Jul 2018
Conference number: 27th (Proceedings)


ConferenceInternational Joint Conference on Artificial Intelligence 2018
Abbreviated titleIJCAI 2018
Internet address


  • Constraints and SAT
  • modeling
  • Formulation
  • Machine Learning
  • Neural Networks
  • Planning and Scheduling:
  • Model-Based Reasoning
  • Other approaches to planning

Cite this