{"id":"https://openalex.org/W4415428281","doi":"https://doi.org/10.3233/faia251077","title":"DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-Domain Reinforcement Learning","display_name":"DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-Domain Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428281","doi":"https://doi.org/10.3233/faia251077"},"language":null,"primary_location":{"id":"doi:10.3233/faia251077","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251077","pdf_url":null,"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://doi.org/10.3233/faia251077","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034960120","display_name":"Linh Le Pham Van","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Linh Le Pham Van","raw_affiliation_strings":["Applied Artificial Intelligence Initiative, Deakin University"],"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Initiative, Deakin University","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436374","display_name":"Minh Hoang Nguyen","orcid":"https://orcid.org/0009-0004-1384-3856"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Minh Hoang Nguyen","raw_affiliation_strings":["Applied Artificial Intelligence Initiative, Deakin University"],"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Initiative, Deakin University","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028613041","display_name":"Duc Kieu","orcid":"https://orcid.org/0009-0008-4359-3383"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Duc Kieu","raw_affiliation_strings":["Applied Artificial Intelligence Initiative, Deakin University"],"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Initiative, Deakin University","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101936199","display_name":"Hung L\u00ea","orcid":"https://orcid.org/0000-0002-3126-184X"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hung Le","raw_affiliation_strings":["Applied Artificial Intelligence Initiative, Deakin University"],"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Initiative, Deakin University","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070103029","display_name":"The Hung Tran","orcid":"https://orcid.org/0000-0003-1223-0834"},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hung The Tran","raw_affiliation_strings":["AI Center, VNPT Media, Vietnam"],"affiliations":[{"raw_affiliation_string":"AI Center, VNPT Media, Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101472308","display_name":"Sunil Gupta","orcid":"https://orcid.org/0000-0002-3308-1930"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sunil Gupta","raw_affiliation_strings":["Applied Artificial Intelligence Initiative, Deakin University"],"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Initiative, Deakin University","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034960120"],"corresponding_institution_ids":["https://openalex.org/I4210164862"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50565561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9605000019073486,"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":0.9605000019073486,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8917999863624573},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7723000049591064},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5419999957084656},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47760000824928284},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4041999876499176},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3785000145435333},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.357699990272522}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8917999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752000093460083},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7723000049591064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6223000288009644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4083999991416931},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251077","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251077","pdf_url":null,"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/faia251077","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251077","pdf_url":null,"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-domain":[0],"offline":[1,11,16,81,152,229],"reinforcement":[2],"learning":[3,205],"(RL)":[4],"seeks":[5],"to":[6,23,33,108,166,189],"enhance":[7],"sample":[8],"efficiency":[9],"in":[10,71,110,117,217],"RL":[12,82,153,230],"by":[13,42,99,178],"utilizing":[14,179],"additional":[15,191],"source":[17,27,101,131,192,209],"datasets.":[18],"A":[19],"key":[20],"challenge":[21,41],"is":[22,69,97,133],"identify":[24],"and":[25,102,106,120,214],"utilize":[26],"samples":[28,193],"that":[29,194,223],"are":[30,195],"most":[31],"relevant":[32],"the":[34,130,137,199],"target":[35,49,66,86,104,138,156,200],"domain.":[36,139],"Existing":[37],"approaches":[38],"address":[39,79],"this":[40,76,180],"measuring":[43],"domain":[44,47,113,123,168,181],"gaps":[45],"through":[46],"classifiers,":[48],"transition":[50],"dynamics":[51],"modeling,":[52],"or":[53],"mutual":[54],"information":[55],"estimation":[56,165],"using":[57],"contrastive":[58],"loss.":[59],"However,":[60],"these":[61,142],"methods":[62],"often":[63],"require":[64],"large":[65,100],"datasets,":[67],"which":[68,96],"impractical":[70],"many":[72],"real-world":[73],"scenarios.":[74],"In":[75],"work,":[77],"we":[78,144,183,221],"cross-domain":[80,151,228],"under":[83],"a":[84,127,147,185],"limited":[85,155],"data":[87,132],"setting,":[88],"identifying":[89],"two":[90],"primary":[91],"challenges:":[92],"(1)":[93],"Dataset":[94],"imbalance,":[95],"caused":[98],"small":[103],"datasets":[105],"leads":[107],"overfitting":[109],"neural":[111,171],"network-based":[112],"gap":[114],"estimators,":[115],"resulting":[116],"uninformative":[118],"measurements;":[119],"(2)":[121],"Partial":[122],"overlap,":[124],"where":[125],"only":[126],"subset":[128],"of":[129],"closely":[134],"aligned":[135,197],"with":[136,154,198,206],"To":[140],"overcome":[141],"issues,":[143],"propose":[145],"DmC,":[146],"novel":[148],"framework":[149],"for":[150],"samples.":[157,210],"Specifically,":[158],"DmC":[159,224],"utilizes":[160],"k-nearest":[161],"neighbor":[162],"(k-NN)":[163],"based":[164],"measure":[167],"proximity":[169],"without":[170],"network":[172],"training,":[173],"effectively":[174],"mitigating":[175],"overfitting.":[176],"Then,":[177],"proximity,":[182],"introduce":[184],"nearest-neighbor-guided":[186],"diffusion":[187],"model":[188],"generate":[190],"better":[196],"domain,":[201],"thus":[202],"enhancing":[203],"policy":[204],"more":[207],"effective":[208],"Through":[211],"theoretical":[212],"analysis":[213],"extensive":[215],"experiments":[216],"diverse":[218],"MuJoCo":[219],"environments,":[220],"demonstrate":[222],"significantly":[225],"outperforms":[226],"state-of-the-art":[227],"methods,":[231],"achieving":[232],"substantial":[233],"performance":[234],"gains.":[235]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}