{"id":"https://openalex.org/W4210665702","doi":"https://doi.org/10.1109/cdc45484.2021.9682909","title":"Inverse Reinforcement Learning for Multi-player Apprentice Games in Continuous-Time Nonlinear Systems","display_name":"Inverse Reinforcement Learning for Multi-player Apprentice Games in Continuous-Time Nonlinear Systems","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4210665702","doi":"https://doi.org/10.1109/cdc45484.2021.9682909"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9682909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682909","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5001862814","display_name":"Bosen Lian","orcid":"https://orcid.org/0000-0002-3275-9551"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bosen Lian","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"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":["The State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Synthetical Automation for Process Industries and 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":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["The State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053089078","display_name":"Ali Davoudi","orcid":"https://orcid.org/0000-0003-2951-442X"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Davoudi","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001862814"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":0.3529,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5179606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"803","last_page":"808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9603000283241272,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.6471138000488281},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6347116231918335},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6041081547737122},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5871665477752686},{"id":"https://openalex.org/keywords/apprenticeship","display_name":"Apprenticeship","score":0.5121960043907166},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3460318148136139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3422884941101074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18201607465744019},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.081674724817276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6471138000488281},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6347116231918335},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6041081547737122},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5871665477752686},{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.5121960043907166},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3460318148136139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3422884941101074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18201607465744019},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.081674724817276},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9682909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682909","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W5108103","https://openalex.org/W1614417283","https://openalex.org/W1968908471","https://openalex.org/W1999874108","https://openalex.org/W2027161089","https://openalex.org/W2070469928","https://openalex.org/W2098774185","https://openalex.org/W2109640889","https://openalex.org/W2113023245","https://openalex.org/W2117675763","https://openalex.org/W2124394479","https://openalex.org/W2134491302","https://openalex.org/W2162009473","https://openalex.org/W2475651303","https://openalex.org/W2484646121","https://openalex.org/W2727450595","https://openalex.org/W2734548765","https://openalex.org/W2946233467","https://openalex.org/W2946954414","https://openalex.org/W2950438991","https://openalex.org/W2964010185","https://openalex.org/W2964098908","https://openalex.org/W2983464671","https://openalex.org/W3008929485","https://openalex.org/W3095316834","https://openalex.org/W3121683757","https://openalex.org/W3156476459","https://openalex.org/W3170519291","https://openalex.org/W3195322794","https://openalex.org/W3200276130","https://openalex.org/W3203504876","https://openalex.org/W4231011685","https://openalex.org/W4301018745","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677555207","https://openalex.org/W6684097133","https://openalex.org/W6747901993","https://openalex.org/W6763248972","https://openalex.org/W6774120382","https://openalex.org/W6796763659"],"related_works":["https://openalex.org/W2130264791","https://openalex.org/W4235622043","https://openalex.org/W2155887593","https://openalex.org/W2102428166","https://openalex.org/W1600547024","https://openalex.org/W3125491562","https://openalex.org/W2239395319","https://openalex.org/W2573907782","https://openalex.org/W2980420562","https://openalex.org/W2141338891"],"abstract_inverted_index":{"We":[0,66],"extend":[1],"the":[2,22,25,35,40,49,63,117,122],"inverse":[3,71,85,95],"reinforcement":[4],"learning":[5,76,81,88],"(inverse":[6],"RL)":[7],"algorithms":[8,33],"to":[9],"multi-player":[10],"apprentice":[11],"games":[12,36],"described":[13],"by":[14,37,100],"nonlinear":[15],"differential":[16],"equations.":[17],"In":[18],"these":[19],"games,":[20],"both":[21],"expert":[23,46,115],"and":[24,55,83,105],"learner":[26,38],"have":[27],"N-player":[28],"control":[29,56,80,87],"inputs.":[30],"Inverse":[31],"RL":[32,72,96],"solve":[34],"reconstructing":[39],"unknown":[41],"cost":[42],"function":[43],"of":[44,51,58,113,124],"each":[45,59],"player":[47],"using":[48,101],"demonstration":[50],"expert\u2019s":[52,103],"behavior":[53,107],"(states":[54],"inputs":[57],"player),":[60],"thereby":[61],"mimicking":[62],"given":[64],"behaviors.":[65],"first":[67],"develop":[68],"a":[69,91],"model-based":[70],"algorithm":[73,97],"with":[74],"two":[75],"stages:":[77],"an":[78,84],"optimal":[79,86],"stage":[82],"stage.":[89],"Then,":[90],"model-free":[92],"off-policy":[93],"integral":[94],"is":[98],"developed":[99],"online":[102],"demonstrations":[104],"learner\u2019s":[106],"trajectories":[108],"without":[109],"knowing":[110],"system":[111],"dynamics":[112],"either":[114],"or":[116],"learner.":[118],"Finally,":[119],"simulations":[120],"verify":[121],"effectiveness":[123],"proposed":[125],"algorithms.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}