{"id":"https://openalex.org/W2069195348","doi":"https://doi.org/10.1109/icsmc.2012.6378020","title":"Inverse reinforcement learning for decentralized non-cooperative multiagent systems","display_name":"Inverse reinforcement learning for decentralized non-cooperative multiagent systems","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2069195348","doi":"https://doi.org/10.1109/icsmc.2012.6378020","mag":"2069195348"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2012.6378020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2012.6378020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5026712929","display_name":"Tummalapalli Sudhamsh Reddy","orcid":null},"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":"Tummalapalli Sudhamsh Reddy","raw_affiliation_strings":["Computer Science Department, University of Texas, Arlington, Arlington, TX, USA","Computer Science Department, University of Texas at Arlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Computer Science Department, University of Texas at Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022189229","display_name":"Vamsikrishna Gopikrishna","orcid":null},"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":"Vamsikrishna Gopikrishna","raw_affiliation_strings":["Computer Science Department, University of Texas, Arlington, Arlington, TX, USA","Computer Science Department, University of Texas at Arlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Computer Science Department, University of Texas at Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022237403","display_name":"Gergely Z\u00e1ruba","orcid":null},"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":"Gergely Zaruba","raw_affiliation_strings":["Computer Science Department, University of Texas, Arlington, Arlington, TX, USA","Computer Science Department, University of Texas at Arlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Computer Science Department, University of Texas at Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047174917","display_name":"Manfred Huber","orcid":"https://orcid.org/0009-0007-0294-9147"},"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":"Manfred Huber","raw_affiliation_strings":["Computer Science Department, University of Texas, Arlington, Arlington, TX, USA","Computer Science Department, University of Texas at Arlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Computer Science Department, University of Texas at Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T11031","display_name":"Game Theory and Applications","score":0.9918000102043152,"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/T11182","display_name":"Auction Theory and Applications","score":0.9847000241279602,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8252776861190796},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.6785690784454346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6562474370002747},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6249393224716187},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5750656127929688},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4539681077003479},{"id":"https://openalex.org/keywords/rational-agent","display_name":"Rational agent","score":0.4393869638442993},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4263647496700287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4079137146472931},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3251377046108246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15930742025375366}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8252776861190796},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.6785690784454346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6562474370002747},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6249393224716187},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5750656127929688},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4539681077003479},{"id":"https://openalex.org/C31772880","wikidata":"https://www.wikidata.org/wiki/Q2666479","display_name":"Rational agent","level":2,"score":0.4393869638442993},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4263647496700287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4079137146472931},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3251377046108246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15930742025375366},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2012.6378020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2012.6378020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1481965470","https://openalex.org/W1566073559","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2067050450","https://openalex.org/W2116442740","https://openalex.org/W2118024052","https://openalex.org/W2124394479","https://openalex.org/W2575731723","https://openalex.org/W2950989964","https://openalex.org/W4252284432","https://openalex.org/W4255047891","https://openalex.org/W6634004297","https://openalex.org/W6677631742"],"related_works":["https://openalex.org/W4206233823","https://openalex.org/W2494202692","https://openalex.org/W2161520603","https://openalex.org/W2612836981","https://openalex.org/W2604958989","https://openalex.org/W2618716983","https://openalex.org/W777283020","https://openalex.org/W2032491180","https://openalex.org/W2620638075","https://openalex.org/W4387141839"],"abstract_inverted_index":{"The":[0,58],"objective":[1],"of":[2,23,33,60,66,82,101,140,158],"inverse":[3,35],"reinforcement":[4,36],"learning":[5,37],"(IRL)":[6],"is":[7,63],"to":[8,38,75,167],"learn":[9,39],"an":[10,91,134],"agent's":[11,18],"reward":[12,41,79,86,173],"function":[13,42,174],"based":[14],"on":[15],"either":[16,52],"the":[17,21,24,31,40,49,67,71,96,99,102,108,128,138,141,156,164,172,189],"policies":[19,100,160],"or":[20,54],"observations":[22],"policy.":[25],"In":[26],"this":[27],"paper":[28],"we":[29,89,161],"address":[30],"issue":[32],"using":[34,182],"in":[43,137,149,155],"a":[44,64,77,122,168,183],"multi":[45],"agent":[46,177,191],"setting,":[47,69],"where":[48,70,98,171],"agents":[50,62,72,103,129],"can":[51,162,178],"cooperate":[53],"be":[55,179],"strictly":[56],"non-cooperative.":[57],"case":[59,97,157],"cooperataing":[61],"subcase":[65],"non-cooperative":[68],"collectively":[73],"try":[74],"maximize":[76],"common":[78,148],"function,":[80],"instead":[81],"maximizing":[83],"their":[84],"individual":[85],"functions.":[87],"Here":[88],"present":[90],"IRL":[92],"algorithm":[93],"that":[94,110,127,154],"considers":[95],"are":[104,130,146],"known.":[105],"We":[106,125,152],"use":[107],"framework":[109],"was":[111],"described":[112],"by":[113],"Ng":[114],"and":[115,118,132],"Russell":[116],"[2001]":[117],"extend":[119],"it":[120],"for":[121,175,188],"Multiagent":[123,150,165],"setting.":[124],"assume":[126],"rational":[131],"follow":[133],"optimal":[135],"policy":[136],"sense":[139],"Nash":[142],"Equilibrium.":[143],"These":[144],"assumptions":[145],"very":[147,184],"systems.":[151],"show":[153],"known":[159],"reduce":[163],"problem":[166],"distributed":[169],"solution":[170],"each":[176],"solved":[180],"independently":[181],"similar":[185],"formulation":[186],"as":[187],"single":[190],"case.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}