{"id":"https://openalex.org/W4414359549","doi":"https://doi.org/10.24963/ijcai.2025/669","title":"Multi-granularity Knowledge Transfer for Continual Reinforcement Learning","display_name":"Multi-granularity Knowledge Transfer for Continual Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359549","doi":"https://doi.org/10.24963/ijcai.2025/669"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/669","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5056483490","display_name":"Chaofan Pan","orcid":"https://orcid.org/0000-0002-0754-7039"},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaofan Pan","raw_affiliation_strings":["Southwestern University of Finance and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwestern University of Finance and Economics","institution_ids":["https://openalex.org/I204831749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045261755","display_name":"Lingfei Ren","orcid":"https://orcid.org/0000-0002-3756-3427"},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfei Ren","raw_affiliation_strings":["Southwestern University of Finance and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwestern University of Finance and Economics","institution_ids":["https://openalex.org/I204831749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111387926","display_name":"Yihui Feng","orcid":"https://orcid.org/0009-0003-7853-9508"},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihui Feng","raw_affiliation_strings":["Southwestern University of Finance and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwestern University of Finance and Economics","institution_ids":["https://openalex.org/I204831749"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linbo Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linbo Xiong","raw_affiliation_strings":["Southwestern University of Finance and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwestern University of Finance and Economics","institution_ids":["https://openalex.org/I204831749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323752","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-7566-2995"},"institutions":[{"id":"https://openalex.org/I4210142037","display_name":"Shanxi University of Traditional Chinese Medicine","ror":"https://ror.org/0522dg826","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142037"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Shanxi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanxi University","institution_ids":["https://openalex.org/I4210142037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049385796","display_name":"Yonghao Li","orcid":"https://orcid.org/0000-0001-5653-4907"},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghao Li","raw_affiliation_strings":["Southwestern University of Finance and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwestern University of Finance and Economics","institution_ids":["https://openalex.org/I204831749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068792201","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0002-8046-722X"},"institutions":[{"id":"https://openalex.org/I204831749","display_name":"Southwestern University of Finance and Economics","ror":"https://ror.org/04ewct822","country_code":"CN","type":"education","lineage":["https://openalex.org/I204831749"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["Southwestern University of Finance and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwestern University of Finance and Economics","institution_ids":["https://openalex.org/I204831749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6012","last_page":"6020"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.7924000024795532,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.7924000024795532,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7734000086784363,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6740999817848206,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.6879000067710876},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5985000133514404},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5891000032424927},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5771999955177307},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.5030999779701233},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4487999975681305},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.41830000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920999884605408},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6879000067710876},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5985000133514404},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5404000282287598},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.26899999380111694}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/669","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Continual":[0,80],"reinforcement":[1,81],"learning":[2,117],"(CRL)":[3],"empowers":[4],"RL":[5,119],"agents":[6],"with":[7],"the":[8,20,24,46,99,104,124,149,152],"ability":[9,102],"to":[10,109,135],"learn":[11],"a":[12,68,85,93,114,129],"sequence":[13],"of":[14,49,88,103,151],"tasks,":[15,43],"accumulating":[16],"knowledge":[17,25,40,56,64,77,144],"learned":[18],"in":[19,54,155],"past":[21],"and":[22,112],"using":[23],"for":[26,75,79,97,142],"problemsolving":[27],"or":[28],"future":[29],"task":[30],"learning.":[31],"However,":[32],"existing":[33],"methods":[34],"often":[35],"focus":[36],"on":[37],"transferring":[38],"fine-grained":[39,115],"across":[41,58],"similar":[42],"which":[44,120],"neglects":[45],"multi-granularity":[47,89,143],"structure":[48],"human":[50],"cognitive":[51],"control,":[52],"resulting":[53],"insufficient":[55],"transfer":[57],"diverse":[59,157],"tasks.":[60],"To":[61],"enhance":[62],"coarse-grained":[63],"transfer,":[65],"we":[66],"propose":[67],"novel":[69],"framework":[70],"called":[71],"MT-Core":[72,83,154],"(as":[73],"shorthand":[74],"Multi-granularity":[76],"Transfer":[78],"learning).":[82],"has":[84],"key":[86],"characteristic":[87],"policy":[90,95,116,131],"learning:":[91],"1)":[92],"coarsegrained":[94],"formulation":[96],"utilizing":[98],"powerful":[100],"reasoning":[101],"large":[105],"language":[106],"model":[107],"(LLM)":[108],"set":[110],"goals,":[111],"2)":[113],"through":[118],"is":[121],"oriented":[122],"by":[123],"goals.":[125],"We":[126],"also":[127],"construct":[128],"new":[130],"library":[132],"(knowledge":[133],"base)":[134],"store":[136],"policies":[137],"that":[138],"can":[139],"be":[140],"retrieved":[141],"transfer.":[145],"Experimental":[146],"results":[147],"demonstrate":[148],"superiority":[150],"proposed":[153],"handling":[156],"CRL":[158],"tasks":[159],"versus":[160],"popular":[161],"baselines.":[162]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}