{"id":"https://openalex.org/W4411724950","doi":"https://doi.org/10.1109/iscas56072.2025.11043787","title":"Hierarchical Reinforcement Learning with Self-Distillation for Resource Scheduling in Complex Resource Networks","display_name":"Hierarchical Reinforcement Learning with Self-Distillation for Resource Scheduling in Complex Resource Networks","publication_year":2025,"publication_date":"2025-05-25","ids":{"openalex":"https://openalex.org/W4411724950","doi":"https://doi.org/10.1109/iscas56072.2025.11043787"},"language":"en","primary_location":{"id":"doi:10.1109/iscas56072.2025.11043787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11043787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"article","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/A5041662715","display_name":"Kexin Zhang","orcid":"https://orcid.org/0009-0007-0229-9412"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kexin Zhang","raw_affiliation_strings":["Beihang University,Hangzhou Innovation Institute,Hangzhou,P. R. China,310000"],"affiliations":[{"raw_affiliation_string":"Beihang University,Hangzhou Innovation Institute,Hangzhou,P. R. China,310000","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043311744","display_name":"Qing Gao","orcid":"https://orcid.org/0000-0002-5395-6175"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Gao","raw_affiliation_strings":["Beihang University,School of Automation Science and Electrical Engineering,Beijing,P. R. China,100191"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Automation Science and Electrical Engineering,Beijing,P. R. China,100191","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041662715"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19493119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9072999954223633,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9072999954223633,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7495137453079224},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456538677215576},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6551446914672852},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5839873552322388},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5742059350013733},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5276994705200195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2785470485687256},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.17983418703079224},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12215578556060791},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06815874576568604},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.06209990382194519}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7495137453079224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456538677215576},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6551446914672852},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5839873552322388},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5742059350013733},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5276994705200195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2785470485687256},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.17983418703079224},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12215578556060791},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06815874576568604},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.06209990382194519},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas56072.2025.11043787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11043787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W2029072478","https://openalex.org/W2038494487","https://openalex.org/W2071302132","https://openalex.org/W2100297710","https://openalex.org/W2133880275","https://openalex.org/W2297435753","https://openalex.org/W2327866891","https://openalex.org/W2520294154","https://openalex.org/W2572001128","https://openalex.org/W2597898076","https://openalex.org/W2810048489","https://openalex.org/W2987861506","https://openalex.org/W3089116250","https://openalex.org/W3127314060","https://openalex.org/W3137609883","https://openalex.org/W3168892396","https://openalex.org/W4288391265","https://openalex.org/W4386075997","https://openalex.org/W4388740254","https://openalex.org/W4395047770"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"The":[0,67],"resource":[1,18,35,46,124],"scheduling":[2,36],"problem":[3,37],"still":[4],"presents":[5],"various":[6],"limitations":[7],"in":[8,38],"traditional":[9],"methods":[10],"when":[11],"dealing":[12],"with":[13,28,42],"a":[14,23,43,58,62],"large":[15],"number":[16],"of":[17,45,52,115],"packages.":[19,47,125],"This":[20],"paper":[21],"proposes":[22],"novel":[24],"hierarchical":[25,63],"reinforcement":[26,64],"learning":[27,65],"self-distillation":[29],"(HRLSD)":[30],"model":[31],"to":[32,92,104],"address":[33],"the":[34,50,53,80,86,89,93,96,101,113],"complex":[39],"service":[40],"networks":[41],"large-scale":[44,123],"To":[48],"reduce":[49],"complexity":[51],"policy":[54],"space,":[55],"we":[56],"introduce":[57],"student-teacher":[59],"encoder":[60,98,103],"as":[61],"model.":[66],"student":[68,94,97],"Q-value":[69,72,91],"and":[70],"teacher":[71,90,102],"are":[73],"obtained":[74],"from":[75,88,100],"two":[76],"separate":[77],"Q-networks":[78],"using":[79],"deep":[81],"Q-learning":[82],"method.":[83],"By":[84],"distilling":[85],"knowledge":[87],"Q-value,":[95],"learns":[99],"enhance":[105],"effectiveness":[106,114],"without":[107],"increasing":[108],"computational":[109],"complexity.":[110],"We":[111],"evaluate":[112],"our":[116],"proposed":[117],"method":[118],"through":[119],"numerical":[120],"examples":[121],"involving":[122]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}