{"id":"https://openalex.org/W4414564138","doi":"https://doi.org/10.1109/tnnls.2025.3606751","title":"Enhancing Reinforcement Learning With Cross-Domain Knowledge Transfer via Seeded Graph Matching","display_name":"Enhancing Reinforcement Learning With Cross-Domain Knowledge Transfer via Seeded Graph Matching","publication_year":2025,"publication_date":"2025-09-25","ids":{"openalex":"https://openalex.org/W4414564138","doi":"https://doi.org/10.1109/tnnls.2025.3606751","pmid":"https://pubmed.ncbi.nlm.nih.gov/40996992"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3606751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3606751","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5005174710","display_name":"Gengzhi Zhang","orcid":"https://orcid.org/0009-0009-7960-2605"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gengzhi Zhang","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0009-7960-2605","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051395807","display_name":"Liang Feng","orcid":"https://orcid.org/0000-0002-8356-7242"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Feng","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-8356-7242","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuefeng Chen","orcid":"https://orcid.org/0000-0001-5195-0936"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Chen","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-5195-0936","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021254405","display_name":"Ke Tang","orcid":"https://orcid.org/0000-0002-6236-2002"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Tang","raw_affiliation_strings":["Department of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6236-2002","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025285243","display_name":"Kay Chen Tan","orcid":"https://orcid.org/0000-0002-6802-2463"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kay Chen Tan","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-6802-2463","affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09023395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"1","first_page":"371","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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":0.9969000220298767,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9513999819755554,"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":0.9399999976158142,"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":0.8115000128746033},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5519000291824341},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5200999975204468},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5002999901771545},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49219998717308044},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.45509999990463257}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8115000128746033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868000268936157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093000173568726},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5467000007629395},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35589998960494995},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3606751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3606751","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40996992","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40996992","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G14860923","display_name":null,"funder_award_id":"PolyU15218622","funder_id":"https://openalex.org/F4320317323","funder_display_name":"Key Research and Development Program of Heilongjiang"},{"id":"https://openalex.org/G217689435","display_name":null,"funder_award_id":"PolyU15215623","funder_id":"https://openalex.org/F4320317323","funder_display_name":"Key Research and Development Program of Heilongjiang"},{"id":"https://openalex.org/G2453363155","display_name":null,"funder_award_id":"CSTB2022NSCQ-MSX1285","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G6699141641","display_name":null,"funder_award_id":"C5052-23G","funder_id":"https://openalex.org/F4320317323","funder_display_name":"Key Research and Development Program of Heilongjiang"},{"id":"https://openalex.org/G8295769195","display_name":null,"funder_award_id":"2022YFC3801700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8875182914","display_name":null,"funder_award_id":"62402069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G908007056","display_name":null,"funder_award_id":"PolyU 15229824","funder_id":"https://openalex.org/F4320317323","funder_display_name":"Key Research and Development Program of Heilongjiang"}],"funders":[{"id":"https://openalex.org/F4320317323","display_name":"Key Research and Development Program of Heilongjiang","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W778742492","https://openalex.org/W1848094219","https://openalex.org/W2032378315","https://openalex.org/W2145339207","https://openalex.org/W2159675343","https://openalex.org/W2164114810","https://openalex.org/W2746553466","https://openalex.org/W2808605874","https://openalex.org/W2911718261","https://openalex.org/W2914949695","https://openalex.org/W2960705509","https://openalex.org/W2962817122","https://openalex.org/W2962819988","https://openalex.org/W2963143232","https://openalex.org/W2964998356","https://openalex.org/W3034815680","https://openalex.org/W3081310128","https://openalex.org/W3088310808","https://openalex.org/W3100789280","https://openalex.org/W3127561923","https://openalex.org/W3158808070","https://openalex.org/W3198359393","https://openalex.org/W3200466256","https://openalex.org/W3206820790","https://openalex.org/W3211583675","https://openalex.org/W4226257065","https://openalex.org/W4297964528","https://openalex.org/W4321780050","https://openalex.org/W4377695283","https://openalex.org/W4382119054","https://openalex.org/W4383112908","https://openalex.org/W4386702654","https://openalex.org/W4392173825","https://openalex.org/W4392796768","https://openalex.org/W4393972734","https://openalex.org/W4401023433"],"related_works":[],"abstract_inverted_index":{"Transfer":[0],"reinforcement":[1,10],"learning":[2,11],"(TRL)":[3],"aims":[4],"to":[5,47,101,148],"boost":[6],"the":[7,28,83,150,172,175,204,207],"efficiency":[8],"of":[9,30,118,174,206],"(RL)":[12],"agents":[13],"by":[14,51,155],"leveraging":[15,156],"knowledge":[16,32,62],"from":[17],"related":[18],"tasks.":[19],"Prior":[20],"research":[21],"primarily":[22],"focuses":[23],"on":[24,78,105,138,161,190],"intradomain":[25],"transfer,":[26],"overlooking":[27],"complexities":[29],"transferring":[31],"across":[33,64],"tasks":[34,66,116,129,154,195],"with":[35,67,196],"differing":[36],"state":[37,69,86],"and":[38,57,70,114,142,152,193],"action":[39,71],"spaces.":[40,123,199],"Recent":[41],"efforts":[42],"in":[43,120],"cross-domain":[44,102],"TRL":[45,103],"aim":[46],"bridge":[48],"this":[49,94,162],"gap":[50],"establishing":[52],"mappings":[53],"between":[54,85,112],"disparate":[55],"source":[56,113,151],"target":[58,115,153,176],"spaces,":[59,87],"thereby":[60],"enabling":[61],"transfer":[63,168],"RL":[65,128,140,177,181],"varied":[68],"configurations.":[72],"However,":[73],"existing":[74],"studies":[75,189],"often":[76],"rely":[77],"strict":[79],"prior":[80],"assumptions":[81],"about":[82],"relationships":[84],"which":[88,109],"limits":[89],"their":[90,121,157],"practical":[91],"generality.":[92],"In":[93,124],"article,":[95],"we":[96,126,164,185],"propose":[97],"a":[98,144,166],"novel":[99],"approach":[100],"based":[104,137],"seeded":[106],"graph":[107,145],"matching,":[108],"enables":[110],"alignment":[111],"regardless":[117],"differences":[119],"state-action":[122,198],"particular,":[125],"model":[127],"as":[130,179],"directed":[131],"graphs,":[132],"identify":[133],"seed":[134],"node":[135],"pairs":[136],"common":[139],"properties,":[141],"devise":[143],"matching":[146],"algorithm":[147,169],"align":[149],"structural":[158],"characteristics.":[159],"Building":[160],"alignment,":[163],"introduce":[165],"policy-based":[167],"that":[170],"improves":[171],"performance":[173],"task":[178],"its":[180],"process":[182],"progresses.":[183],"Finally,":[184],"conduct":[186],"comprehensive":[187],"empirical":[188],"both":[191],"discrete":[192],"continuous":[194],"diverse":[197],"The":[200],"experimental":[201],"results":[202],"validate":[203],"effectiveness":[205],"proposed":[208],"algorithm.":[209]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}