{"id":"https://openalex.org/W3203504876","doi":"https://doi.org/10.1109/tnnls.2021.3114612","title":"Inverse Reinforcement Learning for Adversarial Apprentice Games","display_name":"Inverse Reinforcement Learning for Adversarial Apprentice Games","publication_year":2021,"publication_date":"2021-10-10","ids":{"openalex":"https://openalex.org/W3203504876","doi":"https://doi.org/10.1109/tnnls.2021.3114612","mag":"3203504876","pmid":"https://pubmed.ncbi.nlm.nih.gov/34623278"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3114612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3114612","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5001862814","display_name":"Bosen Lian","orcid":"https://orcid.org/0000-0002-3275-9551"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bosen Lian","raw_affiliation_strings":["University of Texas at Arlington Research Institute, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington Research Institute, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102973745","display_name":"Wenqian Xue","orcid":"https://orcid.org/0000-0002-3670-3854"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqian Xue","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["University of Texas at Arlington Research Institute, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington Research Institute, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001862814"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4516,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.96296167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"34","issue":"8","first_page":"4596","last_page":"4609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9628000259399414,"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":0.7112671732902527},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6584985256195068},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5952572822570801},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.575583815574646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5560916662216187},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4853729009628296},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.46383437514305115},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4596642255783081},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44686949253082275},{"id":"https://openalex.org/keywords/apprenticeship","display_name":"Apprenticeship","score":0.4203207492828369},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4197496771812439},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4179782271385193},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32555678486824036},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19023138284683228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112671732902527},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6584985256195068},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5952572822570801},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.575583815574646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5560916662216187},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4853729009628296},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46383437514305115},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4596642255783081},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44686949253082275},{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.4203207492828369},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4197496771812439},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4179782271385193},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32555678486824036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19023138284683228},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3114612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3114612","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34623278","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34623278","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1742339193","display_name":null,"funder_award_id":"W911NF-20-1-0132","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4155764213","display_name":null,"funder_award_id":"N00014-18-1-2221","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W5108103","https://openalex.org/W1511887321","https://openalex.org/W1519783625","https://openalex.org/W1540685400","https://openalex.org/W1603698551","https://openalex.org/W1614417283","https://openalex.org/W1801976851","https://openalex.org/W1970916399","https://openalex.org/W1999874108","https://openalex.org/W2012451615","https://openalex.org/W2019271926","https://openalex.org/W2026018281","https://openalex.org/W2027161089","https://openalex.org/W2046888764","https://openalex.org/W2096013396","https://openalex.org/W2113023245","https://openalex.org/W2117675763","https://openalex.org/W2132468772","https://openalex.org/W2134491302","https://openalex.org/W2484646121","https://openalex.org/W2734548765","https://openalex.org/W2789386227","https://openalex.org/W2794108217","https://openalex.org/W2800901244","https://openalex.org/W2802441085","https://openalex.org/W2811409798","https://openalex.org/W2883057932","https://openalex.org/W2954682350","https://openalex.org/W2963208223","https://openalex.org/W2963277051","https://openalex.org/W2980903217","https://openalex.org/W3009014967","https://openalex.org/W3009702296","https://openalex.org/W3037298378","https://openalex.org/W3085531353","https://openalex.org/W3088597768","https://openalex.org/W3121683757","https://openalex.org/W3138984732","https://openalex.org/W3156476459","https://openalex.org/W3170519291","https://openalex.org/W3200276130","https://openalex.org/W4252284432","https://openalex.org/W4301018745","https://openalex.org/W6631168379","https://openalex.org/W6632235069","https://openalex.org/W6638440308","https://openalex.org/W6676728370","https://openalex.org/W6677555207","https://openalex.org/W6718092244","https://openalex.org/W6751503080","https://openalex.org/W6753207554","https://openalex.org/W6782915976","https://openalex.org/W6783469618","https://openalex.org/W6789361803","https://openalex.org/W6794270814","https://openalex.org/W6802025844"],"related_works":["https://openalex.org/W2130264791","https://openalex.org/W2502115930","https://openalex.org/W2155887593","https://openalex.org/W4235622043","https://openalex.org/W2102428166","https://openalex.org/W1600547024","https://openalex.org/W3125491562","https://openalex.org/W2239395319","https://openalex.org/W2573907782","https://openalex.org/W2980420562"],"abstract_inverted_index":{"This":[0,69],"article":[1],"proposes":[2],"new":[3,86],"inverse":[4,47,66,76,79,89,177],"reinforcement":[5],"learning":[6,54,59,63,153],"(RL)":[7],"algorithms":[8,126],"to":[9,92,145,191],"solve":[10],"our":[11],"defined":[12],"Adversarial":[13,135],"Apprentice":[14,136],"Games":[15],"for":[16,161,173],"nonlinear":[17],"learner":[18,37,120,139,175,189],"and":[19,60,78,109,140,167,198,203,208],"expert":[20,34,96,108,142],"systems.":[21],"The":[22,99],"games":[23],"are":[24,127,143,196],"solved":[25,169],"by":[26,35],"extracting":[27],"the":[28,73,94,107,119,122,138,141,152,174,184,188,193,206,209,212],"unknown":[29,95],"cost":[30,97,185],"function":[31],"of":[32,52,106,117,163,211],"an":[33,56],"a":[36,45,61,85,171],"using":[38,130],"demonstrated":[39],"expert's":[40,194],"behaviors.":[41],"We":[42],"first":[43],"develop":[44],"model-based":[46],"RL":[48,77,90],"algorithm":[49,70,91,101],"that":[50,183,187],"consists":[51],"two":[53,125,165],"stages:":[55],"optimal":[57,67,80],"control":[58],"second":[62],"based":[64],"on":[65],"control.":[68,81],"also":[71],"clarifies":[72],"relationships":[74],"between":[75],"Then,":[82],"we":[83],"propose":[84],"model-free":[87,100],"integral":[88],"reconstruct":[93],"function.":[98],"only":[102],"needs":[103],"online":[104],"demonstration":[105],"learner's":[110],"trajectory":[111],"data":[112],"without":[113],"knowing":[114],"system":[115],"dynamics":[116],"either":[118],"or":[121],"expert.":[123],"These":[124],"further":[128],"implemented":[129],"neural":[131],"networks":[132],"(NNs).":[133],"In":[134],"Games,":[137],"allowed":[144],"suffer":[146],"from":[147],"different":[148],"adversarial":[149],"attacks":[150],"in":[151,176],"process.":[154],"A":[155],"two-player":[156],"zero-sum":[157],"game":[158],"is":[159,168,181],"formulated":[160],"each":[162],"these":[164],"agents":[166],"as":[170],"subproblem":[172],"RL.":[178],"Furthermore,":[179],"it":[180],"shown":[182],"functions":[186],"learns":[190],"mimic":[192],"behavior":[195],"stabilizing":[197],"not":[199],"unique.":[200],"Finally,":[201],"simulations":[202],"comparisons":[204],"show":[205],"effectiveness":[207],"superiority":[210],"proposed":[213],"algorithms.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}