{"id":"https://openalex.org/W4385286429","doi":"https://doi.org/10.1145/3594409.3594417","title":"Double Actors and Uncertainty-Weighted Critics for Offline Reinforcement Learning","display_name":"Double Actors and Uncertainty-Weighted Critics for Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-03-03","ids":{"openalex":"https://openalex.org/W4385286429","doi":"https://doi.org/10.1145/3594409.3594417"},"language":"en","primary_location":{"id":"doi:10.1145/3594409.3594417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3594409.3594417","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3594409.3594417","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3594409.3594417","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040222042","display_name":"Boyuan Xie","orcid":"https://orcid.org/0009-0009-8866-8024"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohao Xie","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0009-8866-8024","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365157","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-2332-3959"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-2332-3959","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.617,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66094775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9897000193595886,"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":0.8367810845375061},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.66705721616745},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6180114150047302},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6144317388534546},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.5893406867980957},{"id":"https://openalex.org/keywords/pessimism","display_name":"Pessimism","score":0.551918089389801},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5393469333648682},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5375200510025024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354763269424438},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5242600440979004},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45459675788879395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4243178963661194},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33744126558303833},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.23444685339927673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21153610944747925},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1508326232433319}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8367810845375061},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.66705721616745},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6180114150047302},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6144317388534546},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.5893406867980957},{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.551918089389801},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5393469333648682},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5375200510025024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354763269424438},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5242600440979004},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45459675788879395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4243178963661194},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33744126558303833},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.23444685339927673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21153610944747925},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1508326232433319},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3594409.3594417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3594409.3594417","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3594409.3594417","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3594409.3594417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3594409.3594417","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3594409.3594417","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G2262853887","display_name":null,"funder_award_id":"61836011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4198966207","display_name":null,"funder_award_id":"U19B2044","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385286429.pdf","grobid_xml":"https://content.openalex.org/works/W4385286429.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2112420033","https://openalex.org/W2964059111","https://openalex.org/W2982041329","https://openalex.org/W3009584650","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3130177876","https://openalex.org/W3136208045","https://openalex.org/W3170016383","https://openalex.org/W3170872007","https://openalex.org/W3172360140","https://openalex.org/W3185072956","https://openalex.org/W4287118283","https://openalex.org/W6777656069"],"related_works":["https://openalex.org/W1968270095","https://openalex.org/W4296478327","https://openalex.org/W1960072520","https://openalex.org/W2042397106","https://openalex.org/W4380987628","https://openalex.org/W4361730764","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning,":[2],"also":[3],"known":[4],"as":[5],"batch":[6],"RL,":[7,171],"promises":[8],"to":[9,59,106],"learn":[10,107],"policies":[11],"effectively":[12],"from":[13,44],"previously":[14],"collected":[15],"datasets":[16],"without":[17],"exploration.":[18],"But":[19],"lack":[20],"of":[21,66,90,134,185],"interaction":[22],"with":[23,179],"the":[24,28,32,36,41,64,88,140,145,151,159,186],"environment":[25],"continually":[26],"brings":[27],"distribution":[29],"shift":[30],"between":[31],"learned":[33,56],"policy":[34,57,61,152],"and":[35,79,93,114,138],"behavior":[37,60],"policy,":[38],"which":[39],"exacerbates":[40],"extrapolation":[42],"errors":[43],"out-of-distribution":[45],"(OOD)":[46],"actions":[47],"or":[48,62],"states":[49],"when":[50],"bootstrapping.":[51],"Existing":[52],"methods,":[53],"whether":[54],"constraining":[55],"close":[58],"penalizing":[63],"value":[65,100,112,120,136,141],"OOD":[67],"actions,":[68],"are":[69],"too":[70],"pessimistic.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75,123,149],"propose":[76],"Double":[77],"Actors":[78],"Uncertainty-Weighted":[80],"Critics":[81],"(DAUWC),":[82],"an":[83,132],"uncertainty-based":[84],"actor-critic":[85],"method":[86],"exploring":[87],"potential":[89],"double":[91,104],"actors":[92,105],"ensemble":[94,133],"critics":[95],"for":[96,127,169],"efficient":[97],"moderate":[98],"pessimistic":[99],"estimation.":[101],"We":[102],"use":[103],"a":[108,166],"conservative":[109],"optimistic":[110],"state":[111],"function":[113,142],"back":[115],"it":[116],"up":[117],"into":[118],"state-action":[119,135],"functions.":[121],"Meanwhile,":[122],"obtain":[124],"uncertainty":[125],"estimates":[126],"action":[128],"values":[129],"by":[130],"using":[131],"networks":[137],"penalize":[139],"based":[143,157],"on":[144,158,164],"estimated":[146],"uncertainty.":[147],"Finally,":[148],"extract":[150],"via":[153],"advantage-weighted":[154],"behavioral":[155],"cloning":[156],"pre-existing":[160],"framework.":[161],"Experimental":[162],"results":[163],"D4RL,":[165],"standard":[167],"benchmark":[168],"offline":[170],"show":[172],"that":[173],"DAUWC":[174],"significantly":[175],"outperforms":[176],"state-of-the-art":[177],"methods":[178],"higher":[180],"normalized":[181],"scores":[182],"in":[183],"most":[184],"tasks.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}