{"id":"https://openalex.org/W4387185245","doi":"https://doi.org/10.3233/faia230597","title":"Model-Based Offline Policy Optimization with Adversarial Network","display_name":"Model-Based Offline Policy Optimization with Adversarial Network","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185245","doi":"https://doi.org/10.3233/faia230597"},"language":"en","primary_location":{"id":"doi:10.3233/faia230597","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230597","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230597","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/FAIA230597","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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"]},{"id":"https://openalex.org/I4210126530","display_name":"Data Assurance and Communication Security","ror":"https://ror.org/02z2gfm30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210126530","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junming Yang","raw_affiliation_strings":["Jiangsu Key Laboratory of Big Data Security and Intelligent Processing, China","School of Modern Posts, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Big Data Security and Intelligent Processing, China","institution_ids":["https://openalex.org/I4210126530"]},{"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/A5025828195","display_name":"Xingguo Chen","orcid":"https://orcid.org/0000-0002-0221-733X"},"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"]},{"id":"https://openalex.org/I4210126530","display_name":"Data Assurance and Communication Security","ror":"https://ror.org/02z2gfm30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210126530","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingguo Chen","raw_affiliation_strings":["Jiangsu Key Laboratory of Big Data Security and Intelligent Processing, China","School of Computer Science, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Big Data Security and Intelligent Processing, China","institution_ids":["https://openalex.org/I4210126530"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071091495","display_name":"Shengyuan Wang","orcid":"https://orcid.org/0000-0002-9264-4860"},"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":"Shengyuan Wang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108085893","display_name":"Bolei Zhang","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":true,"raw_author_name":"Bolei Zhang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108085893"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":1.0109,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78729398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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":0.9961000084877014,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9567000269889832,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9182999730110168,"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/adversary","display_name":"Adversary","score":0.7490056753158569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.740670919418335},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7318936586380005},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6076006293296814},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5828521251678467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551367998123169},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5082694888114929},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4646662473678589},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.4362420439720154},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.41635558009147644},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35598084330558777},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14585065841674805},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1429782509803772},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09675931930541992}],"concepts":[{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.7490056753158569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.740670919418335},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7318936586380005},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6076006293296814},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5828521251678467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551367998123169},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5082694888114929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4646662473678589},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.4362420439720154},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.41635558009147644},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35598084330558777},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14585065841674805},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1429782509803772},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09675931930541992},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230597","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230597","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230597","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/faia230597","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230597","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230597","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/G5630865570","display_name":null,"funder_award_id":"BK20200752","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G669068149","display_name":null,"funder_award_id":"62276142","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"},{"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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185245.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2105767494","https://openalex.org/W2149306165","https://openalex.org/W2328111639","https://openalex.org/W2434014514","https://openalex.org/W2596367596","https://openalex.org/W2781726626","https://openalex.org/W2805762288","https://openalex.org/W2806690340","https://openalex.org/W2859967432","https://openalex.org/W2896292273","https://openalex.org/W2902907165","https://openalex.org/W2945586853","https://openalex.org/W2947150733","https://openalex.org/W2963277051","https://openalex.org/W2964053787","https://openalex.org/W2978455699","https://openalex.org/W2984869362","https://openalex.org/W2991355586","https://openalex.org/W3002044607","https://openalex.org/W3007990536","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3090832565","https://openalex.org/W3130177876","https://openalex.org/W3166900126","https://openalex.org/W3172360140","https://openalex.org/W3180887884","https://openalex.org/W3199737839","https://openalex.org/W3201700917","https://openalex.org/W3202125656","https://openalex.org/W3205794883","https://openalex.org/W4225110331","https://openalex.org/W4225623389","https://openalex.org/W4226201616","https://openalex.org/W4290858323","https://openalex.org/W4298206671","https://openalex.org/W4302010007"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W4320018150","https://openalex.org/W2918664383","https://openalex.org/W2040808657","https://openalex.org/W4320855730","https://openalex.org/W106056076","https://openalex.org/W2135200719","https://openalex.org/W4225619808"],"abstract_inverted_index":{"Model-based":[0,90],"offline":[1,28,155],"reinforcement":[2],"learning":[3,106],"(RL),":[4],"which":[5],"builds":[6],"a":[7,24,44,88,109,133],"supervised":[8],"transition":[9,57,110],"model":[10,63,111],"with":[11,18,95,112,139],"logging":[12,36],"dataset":[13],"to":[14,54,103,107,120],"avoid":[15],"costly":[16],"interactions":[17],"the":[19,32,35,62,67,71,74,77,128,136,167],"online":[20,39],"environment,":[21],"has":[22],"been":[23],"promising":[25],"approach":[26,147],"for":[27],"policy":[29,92],"optimization.":[30],"As":[31],"discrepancy":[33],"between":[34,122],"data":[37],"and":[38,60,76,124,165],"environment":[40],"may":[41,80],"result":[42],"in":[43],"distributional":[45],"shift":[46],"problem,":[47],"many":[48],"prior":[49],"works":[50],"have":[51],"studied":[52,154],"how":[53],"build":[55,108],"robust":[56],"models":[58],"conservatively":[59],"estimate":[61],"uncertainty":[64,78,138,168],"accurately.":[65,170],"However,":[66],"over-conservatism":[68],"can":[69,130,159],"limit":[70],"exploration":[72],"of":[73,135],"agent,":[75],"estimates":[79],"be":[81],"unreliable.":[82],"In":[83],"this":[84],"work,":[85],"we":[86],"propose":[87],"novel":[89],"Offline":[91],"optimization":[93],"framework":[94],"Adversarial":[96],"Network":[97],"(MOAN).":[98],"The":[99],"key":[100],"idea":[101],"is":[102,118],"use":[104],"adversarial":[105],"better":[113],"generalization,":[114],"where":[115],"an":[116],"adversary":[117,129],"introduced":[119],"distinguish":[121],"in-distribution":[123,163],"out-of-distribution":[125],"samples.":[126],"Moreover,":[127],"naturally":[131],"provide":[132],"quantification":[134],"model\u2019s":[137],"theoretical":[140],"guarantees.":[141],"Extensive":[142],"experiments":[143],"showed":[144],"that":[145],"our":[146],"outperforms":[148],"existing":[149],"state-of-the-art":[150],"baselines":[151],"on":[152],"widely":[153],"RL":[156],"benchmarks.":[157],"It":[158],"also":[160],"generate":[161],"diverse":[162],"samples,":[164],"quantify":[166],"more":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}