{"id":"https://openalex.org/W4381327812","doi":"https://doi.org/10.1109/tcds.2023.3287987","title":"UAC: Offline Reinforcement Learning With Uncertain Action Constraint","display_name":"UAC: Offline Reinforcement Learning With Uncertain Action Constraint","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4381327812","doi":"https://doi.org/10.1109/tcds.2023.3287987"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2023.3287987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3287987","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Transactions on Cognitive and Developmental Systems","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/A5101740669","display_name":"Jiayi Guan","orcid":"https://orcid.org/0000-0003-4097-438X"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiayi Guan","raw_affiliation_strings":["Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062677595","display_name":"Shangding Gu","orcid":"https://orcid.org/0000-0002-2722-3779"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shangding Gu","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450024","display_name":"Zhijun Li","orcid":"https://orcid.org/0000-0002-3909-488X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Li","raw_affiliation_strings":["School of Mechanical Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091579598","display_name":"Jing Hou","orcid":"https://orcid.org/0000-0003-4778-137X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Hou","raw_affiliation_strings":["Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046252455","display_name":"Yiqin Yang","orcid":"https://orcid.org/0000-0002-8748-1964"},"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":"Yiqin Yang","raw_affiliation_strings":["Department of Automation and Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation and Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323037","display_name":"Guang Chen","orcid":"https://orcid.org/0000-0002-7416-592X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang CHen","raw_affiliation_strings":["Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066099338","display_name":"Changjun Jiang","orcid":"https://orcid.org/0000-0003-0637-9317"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjun Jiang","raw_affiliation_strings":["Department of Computer Science, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101740669"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":1.0438,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80923136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":"2","first_page":"671","last_page":"680"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7655141353607178},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6494042873382568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49538862705230713},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.48910242319107056},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45862334966659546},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42544740438461304},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4175500273704529},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41639405488967896},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.41339272260665894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1354038119316101}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655141353607178},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6494042873382568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49538862705230713},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.48910242319107056},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45862334966659546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42544740438461304},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4175500273704529},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41639405488967896},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.41339272260665894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1354038119316101},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2023.3287987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3287987","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319772","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W153021509","https://openalex.org/W192920577","https://openalex.org/W2050630772","https://openalex.org/W2145339207","https://openalex.org/W2569132502","https://openalex.org/W2602871544","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3018036994","https://openalex.org/W3022566517","https://openalex.org/W3034445502","https://openalex.org/W3034652687","https://openalex.org/W3097268408","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3115682199","https://openalex.org/W3129322645","https://openalex.org/W3146823280","https://openalex.org/W3187188159","https://openalex.org/W4214717370","https://openalex.org/W4225937744","https://openalex.org/W4283797777","https://openalex.org/W4292313830","https://openalex.org/W4294691690","https://openalex.org/W4311508998","https://openalex.org/W6693958471","https://openalex.org/W6757469721","https://openalex.org/W6760862771","https://openalex.org/W6761973403","https://openalex.org/W6763704811","https://openalex.org/W6769342953","https://openalex.org/W6771270455","https://openalex.org/W6771886500","https://openalex.org/W6772092215","https://openalex.org/W6774583691","https://openalex.org/W6774823833","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6780159193","https://openalex.org/W6783671239","https://openalex.org/W6785559887","https://openalex.org/W6786103492","https://openalex.org/W6787043984","https://openalex.org/W6790767801","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6792120457","https://openalex.org/W6796289742","https://openalex.org/W6796429164","https://openalex.org/W6796589144","https://openalex.org/W6796880758","https://openalex.org/W6796926305","https://openalex.org/W6796971187","https://openalex.org/W6801801719","https://openalex.org/W6802704075","https://openalex.org/W6804244202","https://openalex.org/W6810070241","https://openalex.org/W6838948168"],"related_works":["https://openalex.org/W1968270095","https://openalex.org/W4296478327","https://openalex.org/W1960072520","https://openalex.org/W2042397106","https://openalex.org/W4361730764","https://openalex.org/W1965029248","https://openalex.org/W2220129715","https://openalex.org/W2387596242","https://openalex.org/W2333625343","https://openalex.org/W2074627651"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"algorithms":[4,44],"promise":[5],"to":[6,50,79,123,153],"learn":[7],"policies":[8],"directly":[9],"from":[10,46],"offline":[11,42,64],"data":[12,175],"sets":[13],"without":[14],"environmental":[15,120],"interaction.":[16],"This":[17],"arrangement":[18],"enables":[19],"successful":[20],"RL":[21,43,65],"applications":[22],"in":[23,28,129,186],"the":[24,40,81,95,103,116,119,130,141,155,159,166,172,187],"real":[25],"world,":[26],"particularly":[27],"robots":[29],"and":[30,37,87,126,147,168],"autonomous":[31],"driving,":[32],"where":[33],"sampling":[34],"is":[35,78,150],"costly":[36],"dangerous.":[38],"However,":[39],"existing":[41],"suffer":[45],"insufficient":[47],"performance":[48],"attributed":[49],"extrapolation":[51,82,104],"error":[52,83],"caused":[53],"by":[54],"out-of-distribution":[55],"(OOD)":[56],"actions.":[57,89,161],"In":[58],"this":[59],"work,":[60],"we":[61,91,109,163],"propose":[62,110],"an":[63,68,111],"algorithm":[66],"with":[67],"uncertain":[69,88,127],"action":[70],"constraint":[71],"(UAC).":[72],"The":[73],"design":[74],"principle":[75],"of":[76,97,100,118,144,158,189],"UAC":[77,181],"minimize":[80],"via":[84],"eliminating":[85],"unknown":[86,125],"Concretely,":[90],"first":[92],"theoretically":[93],"analyze":[94],"effects":[96],"different":[98],"types":[99],"actions":[101,128],"on":[102,107,171],"error.":[105],"Based":[106],"this,":[108],"action-constrained":[112],"strategy":[113],"that":[114,180],"exploits":[115],"uncertainty":[117],"dynamics":[121],"model":[122],"eliminate":[124],"<inline-formula":[131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[133],"<tex-math":[134],"notation=\"LaTeX\">$Q$":[135],"</tex-math></inline-formula>":[136],"-value":[137],"evaluation":[138],"process.":[139],"Furthermore,":[140],"convex":[142],"combination":[143],"trajectory":[145],"information":[146],"Gaussian":[148],"noise":[149],"novelly":[151],"leveraged":[152],"enhance":[154],"generation":[156],"probability":[157],"optimal":[160],"Finally,":[162],"carry":[164],"out":[165],"comparison":[167],"ablation":[169],"experiments":[170],"standard":[173],"D4RL":[174],"set.":[176],"Experimental":[177],"results":[178],"indicate":[179],"achieves":[182],"competitive":[183],"performance,":[184],"especially":[185],"field":[188],"robotic":[190],"manipulation.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}