{"id":"https://openalex.org/W4391621086","doi":"https://doi.org/10.1109/lra.2024.3363530","title":"Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning","display_name":"Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning","publication_year":2024,"publication_date":"2024-02-07","ids":{"openalex":"https://openalex.org/W4391621086","doi":"https://doi.org/10.1109/lra.2024.3363530"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3363530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3363530","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-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/A5043035757","display_name":"Suzan Ece Ada","orcid":"https://orcid.org/0000-0003-1901-8473"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Suzan Ece Ada","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University, Istanbul, Türkiye"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University, Istanbul, Türkiye","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018729334","display_name":"Erhan \u00d6ztop","orcid":"https://orcid.org/0000-0002-3051-6038"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]},{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["JP","TR"],"is_corresponding":false,"raw_author_name":"Erhan Oztop","raw_affiliation_strings":["SISReC, OTRI, Osaka University, Osaka, Japan","Department of Computer Science, Ozyegin University, Istanbul, Turkey","Erhan Oztop is with SISReC, OTRI, Osaka University, Japan, and"],"affiliations":[{"raw_affiliation_string":"SISReC, OTRI, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Department of Computer Science, Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]},{"raw_affiliation_string":"Erhan Oztop is with SISReC, OTRI, Osaka University, Japan, and","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048165304","display_name":"Emre U\u011fur","orcid":"https://orcid.org/0000-0001-9597-2731"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emre Ugur","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University, Istanbul, Türkiye"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University, Istanbul, Türkiye","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043035757"],"corresponding_institution_ids":["https://openalex.org/I4405392"],"apc_list":null,"apc_paid":null,"fwci":3.9544,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94012081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"9","issue":"4","first_page":"3116","last_page":"3123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9832000136375427,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7374007105827332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719520092010498},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6983222365379333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6396751403808594},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6354787349700928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5564859509468079},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1332792043685913}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7374007105827332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719520092010498},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6983222365379333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6396751403808594},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6354787349700928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5564859509468079},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1332792043685913},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2024.3363530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3363530","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/10662","is_oa":false,"landing_page_url":"https://hdl.handle.net/10679/10662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2280667928","display_name":null,"funder_award_id":"JPNP16007","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"},{"id":"https://openalex.org/G2372071177","display_name":null,"funder_award_id":"118E923","funder_id":"https://openalex.org/F4320322626","funder_display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2746553466","https://openalex.org/W2904693122","https://openalex.org/W2947150733","https://openalex.org/W2991355586","https://openalex.org/W3007207078","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3205794883","https://openalex.org/W4214717370","https://openalex.org/W4280638670","https://openalex.org/W4317941989","https://openalex.org/W4385430674","https://openalex.org/W4387195417","https://openalex.org/W4387635994","https://openalex.org/W4387682254","https://openalex.org/W4391971771","https://openalex.org/W6679045638","https://openalex.org/W6684921986","https://openalex.org/W6747473740","https://openalex.org/W6757042666","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6765775151","https://openalex.org/W6771270455","https://openalex.org/W6773034082","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6779823529","https://openalex.org/W6780559895","https://openalex.org/W6791413555","https://openalex.org/W6796176593","https://openalex.org/W6796289742","https://openalex.org/W6796589144","https://openalex.org/W6796926305","https://openalex.org/W6800425027","https://openalex.org/W6802363888","https://openalex.org/W6802659552","https://openalex.org/W6838483015","https://openalex.org/W6841549819","https://openalex.org/W6849515686","https://openalex.org/W6849681998","https://openalex.org/W6857772651"],"related_works":["https://openalex.org/W2768698792","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Offline":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"methods":[4],"leverage":[5],"previous":[6],"experiences":[7],"to":[8,28,64,80],"learn":[9],"better":[10],"policies":[11,63],"than":[12],"the":[13,29,58,66,82,91,133,136,147,159,187,201,207,212,215],"behavior":[14],"policy":[15],"used":[16],"for":[17,47],"data":[18],"collection.":[19],"However,":[20],"they":[21],"face":[22],"challenges":[23],"handling":[24],"distribution":[25,83],"shifts":[26],"due":[27],"lack":[30],"of":[31,61,68,76,97,135,149,161,168,200],"online":[32],"interaction":[33],"during":[34],"training.":[35],"To":[36,89],"this":[37],"end,":[38],"we":[39,99,131,145,177],"propose":[40],"a":[41,101,112,191],"novel":[42,102],"method":[43,73,181],"named":[44],"State":[45],"Reconstruction":[46],"Diffusion":[48],"Policies":[49],"(SRDP)":[50],"that":[51,179],"incorporates":[52],"state":[53,78,138,202],"reconstruction":[54,139],"feature":[55],"learning":[56,75],"in":[57,120],"recent":[59],"class":[60],"diffusion":[62],"address":[65],"problem":[67],"out-of-distribution":[69],"(OOD)":[70],"generalization.":[71],"Our":[72],"promotes":[74],"generalizable":[77],"representation":[79],"alleviate":[81],"shift":[84],"caused":[85],"by":[86],"OOD":[87,92],"states.":[88],"illustrate":[90],"generalization":[93],"and":[94,108,122,165,171],"faster":[95],"convergence":[96],"SRDP,":[98],"design":[100],"2D":[103],"Multimodal":[104],"Contextual":[105],"Bandit":[106],"environment":[107],"realize":[109],"it":[110],"on":[111,152,190],"6-DoF":[113],"real-world":[114],"UR10":[115],"robot,":[116],"as":[117,119],"well":[118],"simulation,":[121],"compare":[123],"its":[124],"performance":[125,148],"with":[126],"prior":[127],"algorithms.":[128],"In":[129,143],"particular,":[130],"show":[132],"importance":[134],"proposed":[137],"via":[140],"ablation":[141],"studies.":[142],"addition,":[144],"assess":[146],"our":[150,180],"model":[151],"standard":[153],"continuous":[154,193],"control":[155,194],"benchmarks":[156],"(D4RL),":[157],"namely":[158],"navigation":[160,195],"an":[162],"8-DoF":[163],"ant":[164],"forward":[166],"locomotion":[167],"half-cheetah,":[169],"hopper,":[170],"walker2d,":[172],"achieving":[173],"state-of-the-art":[174],"results.":[175],"Finally,":[176],"demonstrate":[178],"can":[182],"achieve":[183],"167%":[184],"improvement":[185],"over":[186],"competing":[188],"baseline":[189],"sparse":[192],"task":[196],"where":[197],"various":[198],"regions":[199],"space":[203],"are":[204],"removed":[205],"from":[206],"offline":[208],"RL":[209],"dataset,":[210],"including":[211],"region":[213],"encapsulating":[214],"goal.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}