{"id":"https://openalex.org/W4387171872","doi":"https://doi.org/10.3233/faia230386","title":"Exploration and Exploitation in Hierarchical Reinforcement Learning with Adaptive Scheduling","display_name":"Exploration and Exploitation in Hierarchical Reinforcement Learning with Adaptive Scheduling","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171872","doi":"https://doi.org/10.3233/faia230386"},"language":"en","primary_location":{"id":"doi:10.3233/faia230386","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230386","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230386","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230386","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086179182","display_name":"Zhigang Huang","orcid":"https://orcid.org/0000-0003-1959-2192"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Huang","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, 215006, Suzhou, Jiangsu, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, 215006, Suzhou, Jiangsu, P.R.China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414574","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0002-8710-1810"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quan Liu","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, 215006, Suzhou, Jiangsu, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, 215006, Suzhou, Jiangsu, P.R.China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100414574"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":1.0237,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78807251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9309999942779541,"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":0.9309999942779541,"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/T11182","display_name":"Auction Theory and Applications","score":0.9304999709129333,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9210000038146973,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.746423602104187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7341355085372925},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5642239451408386},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5189461708068848},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.48589247465133667},{"id":"https://openalex.org/keywords/two-level-scheduling","display_name":"Two-level scheduling","score":0.4151898920536041},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33037352561950684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3252961337566376},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.1403806507587433},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08570024371147156},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08294698596000671}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.746423602104187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341355085372925},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5642239451408386},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5189461708068848},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.48589247465133667},{"id":"https://openalex.org/C119948110","wikidata":"https://www.wikidata.org/wiki/Q7858726","display_name":"Two-level scheduling","level":4,"score":0.4151898920536041},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33037352561950684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3252961337566376},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.1403806507587433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08570024371147156},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08294698596000671}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230386","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230386","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230386","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230386","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230386","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230386","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1055180593","display_name":null,"funder_award_id":"61772355","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327518","display_name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171872.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1591713425","https://openalex.org/W1786044565","https://openalex.org/W2057447866","https://openalex.org/W2556477470","https://openalex.org/W2606433045","https://openalex.org/W2754203286","https://openalex.org/W2767354950","https://openalex.org/W2781726626","https://openalex.org/W2788741142","https://openalex.org/W2803281228","https://openalex.org/W2907385442","https://openalex.org/W2950614095","https://openalex.org/W2954142106","https://openalex.org/W2963134677","https://openalex.org/W2963142324","https://openalex.org/W2963438456","https://openalex.org/W2964227312","https://openalex.org/W2971266180","https://openalex.org/W2997250483","https://openalex.org/W3034780381","https://openalex.org/W3036125317","https://openalex.org/W3121879877","https://openalex.org/W3122177264","https://openalex.org/W3201094358","https://openalex.org/W3205046940","https://openalex.org/W3209826517","https://openalex.org/W3212176182","https://openalex.org/W4221153501","https://openalex.org/W4221160937","https://openalex.org/W4225304231","https://openalex.org/W4229447382","https://openalex.org/W4287364117","https://openalex.org/W4288093623","https://openalex.org/W4288289109","https://openalex.org/W4294811414","https://openalex.org/W4297106277","https://openalex.org/W4308538076","https://openalex.org/W4311565450","https://openalex.org/W4312314355","https://openalex.org/W4312458941","https://openalex.org/W4320561357","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W3036719625","https://openalex.org/W2010484697","https://openalex.org/W2545511463","https://openalex.org/W2372008037","https://openalex.org/W2184166483","https://openalex.org/W2978148977","https://openalex.org/W2106332846","https://openalex.org/W1545991362","https://openalex.org/W2167574351","https://openalex.org/W2503553253"],"abstract_inverted_index":{"In":[0],"hierarchical":[1,39],"reinforcement":[2,40],"learning":[3,41],"(HRL),":[4],"continuous":[5,33,65],"options":[6],"provide":[7],"a":[8,136,160],"knowledge":[9],"carrier":[10],"that":[11,156],"is":[12,47,104,124],"more":[13],"aligned":[14],"with":[15,42],"human":[16],"behavior,":[17],"but":[18],"reliable":[19],"scheduling":[20,30,44,63,72,112,158],"methods":[21],"are":[22],"not":[23],"yet":[24],"available.":[25],"To":[26],"design":[27],"an":[28,53,118],"available":[29],"method":[31],"for":[32],"options,":[34,88],"in":[35,113],"this":[36],"paper,":[37],"the":[38,61,79,83,86,90,108,131,145,165],"adaptive":[43,54,111,157],"(HAS)":[45],"algorithm":[46],"proposed.":[48],"It":[49,67],"focuses":[50],"on":[51,69,94,122,164],"achieving":[52],"balance":[55],"between":[56],"exploration":[57],"and":[58,73,85,148,167],"exploitation":[59],"during":[60],"frequent":[62],"of":[64,82,110,115,150],"options.":[66],"builds":[68],"multi-step":[70],"static":[71],"makes":[74],"switching":[75],"decisions":[76],"according":[77],"to":[78,92,106,126],"relative":[80],"advantages":[81],"previous":[84],"estimated":[87],"enabling":[89],"agent":[91],"focus":[93],"different":[95,98],"behaviors":[96],"at":[97],"phases.":[99],"The":[100,141],"expected":[101],"t-step":[102],"distance":[103],"applied":[105],"demonstrate":[107,144],"superiority":[109],"terms":[114],"exploration.":[116],"Furthermore,":[117],"interruption":[119],"incentive":[120],"based":[121],"annealing":[123],"proposed":[125],"alleviate":[127],"excessive":[128],"exploration,":[129],"accelerating":[130],"convergence":[132],"rate.":[133],"We":[134],"develop":[135],"comprehensive":[137],"experimental":[138,142],"analysis":[139],"scheme.":[140],"results":[143],"high":[146],"performance":[147],"robustness":[149],"HAS.":[151],"Moreover,":[152],"it":[153],"provides":[154],"evidence":[155],"has":[159],"positive":[161],"effect":[162],"both":[163],"representation":[166],"option":[168],"policies.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}