onr:"swepub:oai:lup.lub.lu.se:dfe6a76b-540c-4526-b038-f42c7e91cd08"
Search: onr:"swepub:oai:lup.lub.lu.se:dfe6a76b-540c-4526-b038-f42c7e91cd08" > Theoretical and Exp...
- 1 of 1
- Previous record
- Next record
- To hitlist
Theoretical and Experimental Results for Planning with Learned Binarized Neural Network Transition Models
-
- Say, Buser (author)
- Monash University
-
- Devriendt, Jo (author)
- Lund University,Lunds universitet,Institutionen för datavetenskap,Institutioner vid LTH,Lunds Tekniska Högskola,Department of Computer Science,Departments at LTH,Faculty of Engineering, LTH,University of Copenhagen
-
- Nordström, Jakob (author)
- Lund University,Lunds universitet,Institutionen för datavetenskap,Institutioner vid LTH,Lunds Tekniska Högskola,Department of Computer Science,Departments at LTH,Faculty of Engineering, LTH,University of Copenhagen
- show more...
- Simonis, Helmut (editor)
- show less...
- (creator_code:org_t)
- 2020-09-02
- 2020
- English 18 s.
- In: Principles and Practice of Constraint Programming - 26th International Conference, CP 2020, Proceedings. - Cham : Springer International Publishing. - 1611-3349 .- 0302-9743. - 9783030584740 ; 12333, s. 917-934
- Conference paper (peer-reviewed)
Abstract
Subject headings
Close
- We study planning problems where the transition function is described by a learned binarized neural network (BNN). Theoretically, we show that feasible planning with a learned BNN model is NP-complete, and present two new constraint programming models of this task as a mathematical optimization problem. Experimentally, we run solvers for constraint programming, weighted partial maximum satisfiability, 0–1 integer programming, and pseudo-Boolean optimization, and observe that the pseudo-Boolean solver outperforms previous approaches by one to two orders of magnitude. We also investigate symmetry handling for planning problems with learned BNNs over long horizons. While the results here are less clear-cut, we see that exploiting symmetries can sometimes reduce the running time of the pseudo-Boolean solver by up to three orders of magnitude.
Subject headings
- NATURVETENSKAP -- Matematik -- Beräkningsmatematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Computational Mathematics (hsv//eng)
Keyword
- Automated planning
- Binarized neural networks
- Cutting planes reasoning
- Mathematical optimization
- Pseudo-Boolean optimization
- Symmetry
Publication and Content Type
- kon (subject category)
- ref (subject category)
Find in a library
- Principles and Practice of Constraint Programming - 26th International Conferenc... (Search for host publication in LIBRIS)
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Say, Buser
- Devriendt, Jo
- Nordström, Jakob
- Stuckey, Peter J ...
- Simonis, Helmut
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Mathematics
- and Computational Ma ...
- Articles in the publication
- Principles and P ...
- By the university
- Lund University
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
