{"id":"https://openalex.org/W4416749551","doi":"https://doi.org/10.1109/iros60139.2025.11246521","title":"Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning","display_name":"Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749551","doi":"https://doi.org/10.1109/iros60139.2025.11246521"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5108847174","display_name":"Y. M. Ma","orcid":"https://orcid.org/0000-0002-1380-0088"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunchang Ma","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104317863","display_name":"Tenglong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tenglong Liu","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030762555","display_name":"Yixing Lan","orcid":"https://orcid.org/0000-0003-4503-643X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Lan","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102934127","display_name":"Xin Yin","orcid":"https://orcid.org/0000-0001-7718-0466"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yin","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786094","display_name":"Changxin Zhang","orcid":"https://orcid.org/0000-0001-8829-1049"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxin Zhang","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039734738","display_name":"Xinglong Zhang","orcid":"https://orcid.org/0000-0003-0416-0303"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglong Zhang","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5108847174"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19302776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13468","last_page":"13475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7670999765396118,"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":0.7670999765396118,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02319999970495701,"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":0.01600000075995922,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6974999904632568},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6137999892234802},{"id":"https://openalex.org/keywords/conservatism","display_name":"Conservatism","score":0.4867999851703644},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.41530001163482666},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3046000003814697},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.30309998989105225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077999711036682},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6974999904632568},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6137999892234802},{"id":"https://openalex.org/C96640997","wikidata":"https://www.wikidata.org/wiki/Q5163004","display_name":"Conservatism","level":3,"score":0.4867999851703644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4325999915599823},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4066999852657318},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2911087563","https://openalex.org/W2963411833","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2990747716","https://openalex.org/W3127561923","https://openalex.org/W3216656735","https://openalex.org/W4310705874","https://openalex.org/W4386285856","https://openalex.org/W4404738510","https://openalex.org/W4414050520","https://openalex.org/W4414051111","https://openalex.org/W4415797725","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"In":[0],"offline":[1,107,163],"reinforcement":[2],"learning,":[3],"value":[4],"overestimation":[5],"caused":[6],"by":[7],"out-of-distribution":[8],"(OOD)":[9],"actions":[10,41,104,139],"significantly":[11],"limits":[12],"policy":[13,30,90,133,148],"performance.":[14,151],"Recently,":[15],"diffusion":[16,58,77,111,142],"models":[17,78],"have":[18],"been":[19],"leveraged":[20],"for":[21],"their":[22],"strong":[23],"distribution-matching":[24],"capabilities,":[25],"enforcing":[26],"conservatism":[27,48,159],"through":[28],"behavior":[29],"constraints.":[31],"However,":[32],"existing":[33,197],"methods":[34,198],"often":[35],"apply":[36],"indiscriminate":[37],"regularization":[38],"to":[39,79,109],"redundant":[40],"in":[42,46,105,162,189,199],"low-quality":[43],"datasets,":[44],"resulting":[45],"excessive":[47],"and":[49,55,160,172,195],"an":[50],"imbalance":[51],"between":[52,158],"the":[53,100,106,121,127,141,146,169,200],"expressiveness":[54],"efficiency":[56],"of":[57,103,129],"modeling.":[59],"To":[60],"address":[61],"these":[62],"issues,":[63],"we":[64],"propose":[65],"DIffusion":[66],"policies":[67],"with":[68,120],"Value-conditional":[69],"Optimization":[70],"(DIVO),":[71],"a":[72,95,116,155,208],"novel":[73],"approach":[74,153],"that":[75,98,181],"leverages":[76],"generate":[80],"high-quality,":[81],"broadly":[82],"covered":[83],"in-distribution":[84],"state-action":[85],"samples":[86],"while":[87,124],"facilitating":[88],"efficient":[89],"improvement.":[91],"Specifically,":[92],"DIVO":[93,135,167,182],"introduces":[94],"binary-weighted":[96],"mechanism":[97],"utilizes":[99],"advantage":[101],"values":[102],"dataset":[108],"guide":[110],"model":[112],"training.":[113],"This":[114,152],"enables":[115],"more":[117],"precise":[118],"alignment":[119],"dataset\u2019s":[122],"distribution":[123],"selectively":[125],"expanding":[126],"boundaries":[128],"high-advantage":[130],"actions.":[131],"During":[132],"improvement,":[134],"dynamically":[136],"filters":[137],"high-return-potential":[138],"from":[140],"model,":[143],"effectively":[144],"guiding":[145],"learned":[147],"toward":[149],"better":[150],"achieves":[154,183],"critical":[156],"balance":[157],"explorability":[161],"RL.":[164],"We":[165],"evaluate":[166],"on":[168],"D4RL":[170],"benchmark":[171],"compare":[173],"it":[174],"against":[175],"state-of-the-art":[176],"baselines.":[177],"Empirical":[178],"results":[179],"demonstrate":[180],"superior":[184],"performance,":[185],"delivering":[186],"significant":[187],"improvements":[188],"average":[190],"returns":[191],"across":[192],"locomotion":[193],"tasks":[194],"outperforming":[196],"challenging":[201],"AntMaze":[202],"domain,":[203],"where":[204],"sparse":[205],"rewards":[206],"pose":[207],"major":[209],"difficulty.":[210]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}