{"id":"https://openalex.org/W4387185204","doi":"https://doi.org/10.3233/faia230562","title":"SDV: Simple Double Validation Model-Based Offline Reinforcement Learning","display_name":"SDV: Simple Double Validation Model-Based Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185204","doi":"https://doi.org/10.3233/faia230562"},"language":"en","primary_location":{"id":"doi:10.3233/faia230562","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230562","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230562","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230562","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100722971","display_name":"Xun Wang","orcid":"https://orcid.org/0000-0002-2479-6571"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767769","display_name":"Haonan Chen","orcid":"https://orcid.org/0000-0001-8885-5051"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Chen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010461759","display_name":"Junming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junming Yang","raw_affiliation_strings":["School of Modern Posts, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Modern Posts, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015547394","display_name":"Zhuzhong Qian","orcid":"https://orcid.org/0000-0003-1625-7575"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuzhong Qian","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-1625-7575","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076424029","display_name":"Bolei Zhang","orcid":"https://orcid.org/0000-0002-9406-4499"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bolei Zhang","raw_affiliation_strings":["School of Computer, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-9406-4499","affiliations":[{"raw_affiliation_string":"School of Computer, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076424029"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31355403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.965399980545044,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.965399980545044,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9135000109672546,"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":0.7963885068893433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7666597366333008},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.738502025604248},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6052466034889221},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.526276171207428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5187478065490723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47743090987205505},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.44082796573638916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10190504789352417}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7963885068893433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666597366333008},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.738502025604248},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6052466034889221},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.526276171207428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187478065490723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47743090987205505},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.44082796573638916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10190504789352417},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230562","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230562","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230562","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230562","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230562","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230562","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2227299984","display_name":null,"funder_award_id":"62202238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2475758149","display_name":"\u57fa\u4e8e\u8fb9\u7f18\u8ba1\u7b97\u7684\u4e91\u7aef\u878d\u5408\u7406\u8bba\u65b9\u6cd5\u4e0e\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61832005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5630865570","display_name":null,"funder_award_id":"BK20200752","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185204.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W192920577","https://openalex.org/W2145339207","https://openalex.org/W2157444450","https://openalex.org/W2575705757","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2904453761","https://openalex.org/W2947150733","https://openalex.org/W2950624398","https://openalex.org/W2969281871","https://openalex.org/W2981030070","https://openalex.org/W2991355586","https://openalex.org/W3003533476","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3121045039","https://openalex.org/W3122329924","https://openalex.org/W3127561923","https://openalex.org/W3130177876","https://openalex.org/W3136208045","https://openalex.org/W3154938165","https://openalex.org/W3166795773","https://openalex.org/W3185072956","https://openalex.org/W3201700917","https://openalex.org/W3202125656","https://openalex.org/W3205794883","https://openalex.org/W3212886219","https://openalex.org/W3216656735","https://openalex.org/W4225110331","https://openalex.org/W4283076713","https://openalex.org/W4286908116","https://openalex.org/W4287209565","https://openalex.org/W4288319859","https://openalex.org/W4306818327"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W1707372784","https://openalex.org/W4225619808"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"aims":[4],"to":[5,53,65,91,97,114,124,135],"learn":[6,35],"effective":[7],"policies":[8],"from":[9],"recorded":[10],"data":[11],"without":[12],"further":[13],"interactions":[14],"in":[15,101],"the":[16,36,39,55,60,99,103,106,121,130,146,158,164,174],"environments":[17],"that":[18,117],"are":[19],"often":[20],"costly":[21],"or":[22],"risky.":[23],"Model-based":[24],"algorithms,":[25],"which":[26],"begin":[27],"by":[28,59],"constructing":[29],"an":[30,93,110],"environmental":[31],"model":[32,61,96,170],"and":[33,152,169],"then":[34],"policy":[37],"under":[38],"model,":[40],"have":[41,50],"become":[42],"a":[43,74],"promising":[44],"approach.":[45],"However,":[46],"most":[47],"existing":[48],"works":[49],"been":[51],"over-conservative":[52],"avoid":[54,115],"out-of-distribution":[56],"error":[57],"induced":[58],"generated":[62],"samples,":[63],"leading":[64],"poor":[66],"performance":[67],"instead.":[68],"In":[69,127],"this":[70,128],"work,":[71],"we":[72],"propose":[73],"novel":[75],"model-based":[76,177],"offline":[77,149,178],"RL":[78,150],"method,":[79],"named":[80],"Simple":[81],"Double":[82],"Validation":[83],"(SDV).":[84],"The":[85],"main":[86],"idea":[87,165],"of":[88,105,166,176],"SDV":[89,144],"is":[90],"introduce":[92],"additional":[94],"guidance":[95],"assist":[98],"agent":[100,131],"determining":[102],"rationality":[104],"states,":[107],"combined":[108],"with":[109,139],"advantage":[111,171],"weighting":[112,172],"factor":[113],"effects":[116],"could":[118],"potentially":[119],"mislead":[120],"models":[122],"due":[123],"suboptimal":[125],"samples.":[126],"way,":[129],"can":[132],"be":[133],"guided":[134],"more":[136],"favourable":[137],"states":[138],"reliable":[140],"decisions.":[141],"We":[142],"evaluated":[143],"on":[145],"widely":[147],"studied":[148],"benchmarks":[151],"demonstrated":[153],"its":[154],"state-of-the-art":[155],"performance.":[156],"At":[157],"same":[159],"time,":[160],"our":[161],"work":[162],"introduces":[163],"double":[167],"validation":[168],"into":[173],"field":[175],"RL,":[179],"providing":[180],"new":[181],"insights":[182],"for":[183],"future":[184],"research.":[185]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}