{"id":"https://openalex.org/W7138133154","doi":"https://doi.org/10.1609/aaai.v40i32.39916","title":"Behavior Regularization with Flow Latent Policy for Offline Reinforcement Learning","display_name":"Behavior Regularization with Flow Latent Policy for Offline Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138133154","doi":"https://doi.org/10.1609/aaai.v40i32.39916"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i32.39916","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39916","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39916/43877","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39916/43877","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129673042","display_name":"Yulong Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Xia","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129684222","display_name":"Fuchun Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"32","first_page":"27028","last_page":"27036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5597000122070312,"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":0.5597000122070312,"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":0.06880000233650208,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.04729999974370003,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7074000239372253},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6011999845504761},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5922999978065491},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3919000029563904},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.39089998602867126},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.375900000333786},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.37549999356269836}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7074000239372253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064999938011169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6035000085830688},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579200029373169},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.39089998602867126},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i32.39916","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39916","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39916/43877","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"},{"id":"pmh:oai:ojs.aaai.org:article/39916","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i32.39916","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39916","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39916/43877","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":[],"awards":[{"id":"https://openalex.org/G2388429035","display_name":null,"funder_award_id":"U22B2042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2864656723","display_name":null,"funder_award_id":"No. U22B2042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6033659780","display_name":null,"funder_award_id":"U22A2057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138133154.pdf","grobid_xml":"https://content.openalex.org/works/W7138133154.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Expressive":[0],"generative":[1,110],"models":[2,25],"have":[3],"recently":[4],"shown":[5],"promise":[6],"in":[7,61],"offline":[8,50],"reinforcement":[9],"learning":[10],"(RL)":[11],"by":[12,58],"capturing":[13],"the":[14,37,62,84,109,114,129],"complex,":[15,88],"multimodal":[16],"structure":[17],"of":[18,39,65,131],"dataset":[19],"behavior.":[20],"However,":[21],"directly":[22],"integrating":[23],"these":[24],"into":[26],"policy":[27,78,103],"optimization":[28,57,104],"introduces":[29],"substantial":[30],"computational":[31],"and":[32,101,134],"stability":[33],"challenges":[34],"due":[35],"to":[36,86],"intricacies":[38],"their":[40],"sampling":[41],"processes.":[42],"We":[43],"introduce":[44],"Flow":[45],"Latent":[46],"Policy":[47],"(FLP),":[48],"an":[49],"RL":[51],"framework":[52],"that":[53,118],"decouples":[54],"expressivity":[55],"from":[56],"operating":[59],"entirely":[60],"latent":[63,76],"space":[64],"a":[66,74],"pre-trained,":[67],"frozen":[68],"flow-based":[69],"behavior":[70,95],"model.":[71,111],"FLP":[72,119],"learns":[73],"simple":[75],"Gaussian":[77],"whose":[79],"samples":[80],"are":[81],"transformed":[82],"through":[83,108],"flow":[85],"produce":[87],"behavior-aligned":[89],"actions.":[90],"This":[91],"design":[92],"enables":[93],"closed-form":[94],"regularization":[96],"via":[97],"latent-space":[98],"KL":[99],"divergence":[100],"allows":[102],"without":[105],"expensive":[106],"backpropagation":[107],"Experiments":[112],"on":[113],"OGBench":[115],"benchmark":[116],"demonstrate":[117],"achieves":[120],"competitive":[121],"or":[122],"superior":[123],"performance":[124],"across":[125],"diverse":[126],"tasks,":[127],"combining":[128],"benefits":[130],"expressive":[132],"modeling":[133],"tractable":[135],"optimization.":[136]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}