{"id":"https://openalex.org/W2883869105","doi":"https://doi.org/10.1109/robio.2018.8665177","title":"Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration","display_name":"Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2883869105","doi":"https://doi.org/10.1109/robio.2018.8665177","mag":"2883869105"},"language":"en","primary_location":{"id":"doi:10.1109/robio.2018.8665177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2018.8665177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083545249","display_name":"Tingguang Li","orcid":"https://orcid.org/0000-0003-1161-9987"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tingguang Li","raw_affiliation_strings":["The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074052441","display_name":"Jin Pan","orcid":"https://orcid.org/0000-0003-0753-8754"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jin Pan","raw_affiliation_strings":["The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072234330","display_name":"Delong Zhu","orcid":"https://orcid.org/0000-0002-1143-7860"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Delong Zhu","raw_affiliation_strings":["The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021531143","display_name":"Max Q.\u2010H. Meng","orcid":"https://orcid.org/0000-0002-5255-5898"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Max Q.-H. Meng","raw_affiliation_strings":["The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"648","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8555703163146973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8042405247688293},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7473236322402954},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6396411061286926},{"id":"https://openalex.org/keywords/interrupt","display_name":"Interrupt","score":0.6085883378982544},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5879033803939819},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5856122374534607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5500791668891907},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5267618894577026},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48427289724349976},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45583203434944153},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38583627343177795},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3540556728839874},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3224617838859558},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.13557928800582886},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11220654845237732},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09593477845191956}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8555703163146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042405247688293},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7473236322402954},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6396411061286926},{"id":"https://openalex.org/C41661131","wikidata":"https://www.wikidata.org/wiki/Q220764","display_name":"Interrupt","level":3,"score":0.6085883378982544},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5879033803939819},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5856122374534607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5500791668891907},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5267618894577026},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48427289724349976},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45583203434944153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38583627343177795},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3540556728839874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3224617838859558},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.13557928800582886},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11220654845237732},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09593477845191956},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio.2018.8665177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2018.8665177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1592847719","https://openalex.org/W2109910161","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2153874061","https://openalex.org/W2155027007","https://openalex.org/W2766447205","https://openalex.org/W2891234582","https://openalex.org/W2963262099","https://openalex.org/W2964043796","https://openalex.org/W2964118262","https://openalex.org/W2964227312","https://openalex.org/W4214717370","https://openalex.org/W4249441547","https://openalex.org/W6682998330","https://openalex.org/W6683204974","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6704665273","https://openalex.org/W6727349600"],"related_works":["https://openalex.org/W4288898221","https://openalex.org/W2358308054","https://openalex.org/W2391783641","https://openalex.org/W2109690896","https://openalex.org/W4231875098","https://openalex.org/W4230529130","https://openalex.org/W2391365542","https://openalex.org/W2361731841","https://openalex.org/W2386367690","https://openalex.org/W4243198198"],"abstract_inverted_index":{"To":[0,102],"achieve":[1],"scenario":[2],"intelligence,":[3],"humans":[4],"must":[5],"transfer":[6],"knowledge":[7,52],"to":[8,18,91,98],"robots":[9],"by":[10,69],"developing":[11],"goal-oriented":[12],"algorithms,":[13],"which":[14,50,141],"are":[15],"sometimes":[16],"insensitive":[17],"dynamically":[19],"changing":[20],"environments.":[21],"While":[22],"deep":[23],"reinforcement":[24,58],"learning":[25,59],"achieves":[26],"significant":[27],"success":[28],"recently,":[29],"the":[30,77,94,99,125,143],"long":[31],"and":[32,80,118,138,145],"difficult":[33],"training":[34,78,122],"process":[35,79],"limits":[36],"its":[37],"application.":[38],"In":[39,124],"this":[40,104],"paper,":[41],"we":[42,106],"propose":[43],"a":[44,56,108,120],"hybrid":[45],"structure":[46],"named":[47],"Option-Interruption":[48],"in":[49,132],"human":[51],"is":[53,130],"embedded":[54],"into":[55],"hierarchical":[57],"framework.":[60,149],"Our":[61],"architecture":[62],"has":[63],"two":[64,133],"key":[65],"components:":[66],"options,":[67],"represented":[68],"existing":[70],"human-designed":[71],"methods,":[72],"can":[73],"significantly":[74],"speed":[75],"up":[76],"interruption":[81],"mechanism,":[82],"based":[83,113],"on":[84,114],"learnable":[85],"termination":[86],"functions,":[87],"enables":[88],"our":[89,128,148],"system":[90],"timely":[92],"terminate":[93],"current":[95],"option":[96],"according":[97],"external":[100],"environment.":[101],"implement":[103],"architecture,":[105],"derive":[107],"set":[109],"of":[110,147],"update":[111],"rules":[112],"policy":[115],"gradient":[116],"methods":[117],"present":[119],"complete":[121],"process.":[123],"experiment":[126],"part,":[127],"method":[129],"evaluated":[131],"simulated":[134],"tasks,":[135],"Four-room":[136],"navigation":[137],"exploration":[139],"task,":[140],"shows":[142],"efficiency":[144],"flexibility":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}