{"id":"https://openalex.org/W7138023389","doi":"https://doi.org/10.1609/aaai.v40i26.39342","title":"Enhancing Diffusion Policies with Distribution-Matching Generator in Offline Reinforcement Learning","display_name":"Enhancing Diffusion Policies with Distribution-Matching Generator in Offline Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138023389","doi":"https://doi.org/10.1609/aaai.v40i26.39342"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i26.39342","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39342","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39342/43303","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39342/43303","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129744124","display_name":"Xuemin Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110997","display_name":"Ministry of Education","ror":"https://ror.org/01xexqx38","country_code":"ME","type":"government","lineage":["https://openalex.org/I4210110997"]},{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN","ME"],"is_corresponding":true,"raw_author_name":"Xuemin Hu","raw_affiliation_strings":["Hubei University\nKey Laboratory of Intelligent Sensing System and Security (Hubei University), Ministry of Education"],"affiliations":[{"raw_affiliation_string":"Hubei University\nKey Laboratory of Intelligent Sensing System and Security (Hubei University), Ministry of Education","institution_ids":["https://openalex.org/I75900474","https://openalex.org/I4210110997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746680","display_name":"Shen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Li","raw_affiliation_strings":["Hubei University\nTongji University"],"affiliations":[{"raw_affiliation_string":"Hubei University\nTongji University","institution_ids":["https://openalex.org/I75900474","https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101379644","display_name":"Yingfen Xu","orcid":"https://orcid.org/0009-0000-1251-7574"},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfen Xu","raw_affiliation_strings":["Hubei University"],"affiliations":[{"raw_affiliation_string":"Hubei University","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129742540","display_name":"Bo Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Tang","raw_affiliation_strings":["Worcester Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129713475","display_name":"Long Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Institute of automation, Chinese academy of science, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129744124"],"corresponding_institution_ids":["https://openalex.org/I4210110997","https://openalex.org/I75900474"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24826851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"26","first_page":"21894","last_page":"21902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.42010000348091125,"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":0.42010000348091125,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.18639999628067017,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.06430000066757202,"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/discriminator","display_name":"Discriminator","score":0.9415000081062317},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7957000136375427},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7156000137329102},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5582000017166138},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5202999711036682},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.48080000281333923},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3571000099182129}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9415000081062317},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7957000136375427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462000250816345},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7156000137329102},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5582000017166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573999881744385},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45899999141693115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i26.39342","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39342","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39342/43303","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i26.39342","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39342","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39342/43303","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7735121250152588}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4617895389","display_name":null,"funder_award_id":"300000","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5616351183","display_name":null,"funder_award_id":"00000","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5759134348","display_name":null,"funder_award_id":"62273135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G602373218","display_name":null,"funder_award_id":"2025AFA083","funder_id":"https://openalex.org/F4320322186","funder_display_name":"Natural Science Foundation of Hubei Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null},{"id":"https://openalex.org/F4320329781","display_name":"Hubei University","ror":"https://ror.org/03a60m280"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138023389.pdf","grobid_xml":"https://content.openalex.org/works/W7138023389.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,70],"(RL)":[3],"can":[4],"learn":[5,33],"policies":[6],"from":[7,19,110],"pre-collected":[8],"offline":[9,57],"datasets":[10],"without":[11],"interacting":[12],"with":[13,114],"the":[14,20,28,40,44,76,80,85,89,108,115,127,131],"environment,":[15],"but":[16,35],"it":[17],"suffers":[18],"issue":[21],"of":[22,42,87,117],"out-of-distribution":[23],"(OOD).":[24],"Recent":[25],"methods":[26],"use":[27],"generative":[29,119],"adversarial":[30,120],"paradigm":[31],"to":[32,38,83,106],"policies,":[34],"easily":[36],"fail":[37],"handle":[39,84],"conflict":[41,86],"fooling":[43,88],"discriminator":[45,90,102],"and":[46,91,130],"maximizing":[47,92],"expected":[48,93],"returns.":[49,94],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"a":[55,96],"novel":[56],"RL":[58],"method":[59,71],"named":[60],"Distribution-Matching":[61],"Generator-based":[62],"Diffusion":[63],"Policies":[64],"(DMGDP).":[65],"A":[66],"distribution":[67],"matching-based":[68],"policy":[69,81,97],"is":[72,104],"first":[73],"developed,":[74],"where":[75],"diffusion":[77],"serves":[78],"as":[79],"generator,":[82],"Furthermore,":[95],"confidence":[98],"mechanism":[99],"based":[100],"on":[101,126],"regularization":[103],"designed":[105],"prevent":[107],"agent":[109],"taking":[111],"OOD":[112],"actions,":[113],"aim":[116],"robust":[118],"learning.":[121],"We":[122],"conducted":[123],"extensive":[124],"experiments":[125],"D4RL":[128],"benchmarks,":[129],"results":[132],"demonstrate":[133],"that":[134],"DMGDP":[135],"outperforms":[136],"state-of-the-art":[137],"methods.":[138]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}