File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Learn to Floorplan through Acquisition of Effective Local Search Heuristics

TitleLearn to Floorplan through Acquisition of Effective Local Search Heuristics
Authors
KeywordsFloorplanning
sequence pair
reinforcement learning
Issue Date2020
PublisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1000129/all-proceedings
Citation
Proceedings of 2020 IEEE 38th International Conference on Computer Design (ICCD), Hartford, CT, USA, 18-21 October 2020, p. 324-331 How to Cite?
AbstractAutomatic heuristic design through reinforcement learning opens a promising direction for solving computationally difficult problems. Unlike most previous works that aimed at solution construction, we explore the possibility of acquiring local search heuristics through massive search experiments. To illustrate the applicability, an agent is trained to perform a walk in the search space by selecting a candidate neighbor solution at each step. Specifically, we target the floorplanning problem, where a neighbor solution is generated through perturbing the sequence pair encoding of a floorplan. Experimental results demonstrate the efficacy of the acquired heuristics as well as the potential of automatic heuristic design.
Persistent Identifierhttp://hdl.handle.net/10722/302131
ISSN
2023 SCImago Journal Rankings: 0.466
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorHe, Z-
dc.contributor.authorMa, Y-
dc.contributor.authorZhang, L-
dc.contributor.authorLiao, P-
dc.contributor.authorWong, N-
dc.contributor.authorYu, B-
dc.contributor.authorWong, MDF-
dc.date.accessioned2021-08-21T03:32:01Z-
dc.date.available2021-08-21T03:32:01Z-
dc.date.issued2020-
dc.identifier.citationProceedings of 2020 IEEE 38th International Conference on Computer Design (ICCD), Hartford, CT, USA, 18-21 October 2020, p. 324-331-
dc.identifier.issn1063-6404-
dc.identifier.urihttp://hdl.handle.net/10722/302131-
dc.description.abstractAutomatic heuristic design through reinforcement learning opens a promising direction for solving computationally difficult problems. Unlike most previous works that aimed at solution construction, we explore the possibility of acquiring local search heuristics through massive search experiments. To illustrate the applicability, an agent is trained to perform a walk in the search space by selecting a candidate neighbor solution at each step. Specifically, we target the floorplanning problem, where a neighbor solution is generated through perturbing the sequence pair encoding of a floorplan. Experimental results demonstrate the efficacy of the acquired heuristics as well as the potential of automatic heuristic design.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1000129/all-proceedings-
dc.relation.ispartofIEEE International Conference on Computer Design (ICCD)-
dc.rightsIEEE International Conference on Computer Design (ICCD). Copyright © IEEE.-
dc.rights©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectFloorplanning-
dc.subjectsequence pair-
dc.subjectreinforcement learning-
dc.titleLearn to Floorplan through Acquisition of Effective Local Search Heuristics-
dc.typeConference_Paper-
dc.identifier.emailWong, N: nwong@eee.hku.hk-
dc.identifier.authorityWong, N=rp00190-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICCD50377.2020.00061-
dc.identifier.scopuseid_2-s2.0-85098843749-
dc.identifier.hkuros324492-
dc.identifier.spage324-
dc.identifier.epage331-
dc.identifier.isiWOS:000652198500049-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats