{"id":"https://openalex.org/W3012430540","doi":"https://doi.org/10.1109/cdc40024.2019.9029772","title":"Off-Policy Reinforcement-Learning Algorithm to Solve Minimax Games on Graphs","display_name":"Off-Policy Reinforcement-Learning Algorithm to Solve Minimax Games on Graphs","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3012430540","doi":"https://doi.org/10.1109/cdc40024.2019.9029772","mag":"3012430540"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","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/A5059736491","display_name":"Victor G. Lopez","orcid":"https://orcid.org/0000-0003-3989-4091"},"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":"Victor G. Lopez","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["The Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029213376","display_name":"Yan Wan","orcid":"https://orcid.org/0000-0002-7508-5833"},"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":"Yan Wan","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","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":["Department of Electrical Engineering, University of Texas at Arlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26960872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"23","issue":null,"first_page":"6473","last_page":"6478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9994000196456909,"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":0.9994000196456909,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9919000267982483,"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/minimax","display_name":"Minimax","score":0.9356696605682373},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8384020328521729},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6976046562194824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6152504086494446},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6124176383018494},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5126189589500427},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.45209863781929016},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.42803844809532166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3072930574417114},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21253174543380737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1875191330909729},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.1291237771511078}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.9356696605682373},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8384020328521729},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6976046562194824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6152504086494446},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6124176383018494},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5126189589500427},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.45209863781929016},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.42803844809532166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3072930574417114},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21253174543380737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1875191330909729},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1291237771511078},{"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:10.1109/cdc40024.2019.9029772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W575429305","https://openalex.org/W992293908","https://openalex.org/W1578630563","https://openalex.org/W1614417283","https://openalex.org/W1876438114","https://openalex.org/W1912694276","https://openalex.org/W1994203036","https://openalex.org/W2005437559","https://openalex.org/W2007672844","https://openalex.org/W2016968002","https://openalex.org/W2019478222","https://openalex.org/W2042106612","https://openalex.org/W2046888764","https://openalex.org/W2065632630","https://openalex.org/W2069484364","https://openalex.org/W2072718225","https://openalex.org/W2108383324","https://openalex.org/W2113127719","https://openalex.org/W2121831660","https://openalex.org/W2146804198","https://openalex.org/W2147539438","https://openalex.org/W2148439597","https://openalex.org/W2160643434","https://openalex.org/W2402263400","https://openalex.org/W2484646121","https://openalex.org/W2498694880","https://openalex.org/W2531648764","https://openalex.org/W2580211036","https://openalex.org/W3101425602","https://openalex.org/W4252284432","https://openalex.org/W6642419673","https://openalex.org/W6682089242"],"related_works":["https://openalex.org/W2016058626","https://openalex.org/W2474724840","https://openalex.org/W2963760573","https://openalex.org/W4312141693","https://openalex.org/W1536009559","https://openalex.org/W2103821767","https://openalex.org/W1969185016","https://openalex.org/W2037619003","https://openalex.org/W2111030377","https://openalex.org/W1965856819"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,51],"formulate":[4],"and":[5,66,70],"find":[6],"distributed":[7,33],"minimax":[8,45,63],"strategies":[9,16],"as":[10],"an":[11,53],"alternative":[12],"to":[13,60],"Nash":[14],"equilibrium":[15],"for":[17,31],"multi-agent":[18],"systems":[19],"communicating":[20],"via":[21],"graph":[22],"topologies,":[23],"i.e.,":[24],"communication":[25],"restrictions":[26],"are":[27],"taken":[28],"into":[29],"account":[30],"the":[32,37,41,44,48,62,68,74,80],"design.":[34],"We":[35],"provide":[36],"conditions":[38],"that":[39],"guarantee":[40],"existence":[42],"of":[43,73],"solutions":[46],"in":[47],"game.":[49],"Finally,":[50],"present":[52],"off-policy":[54],"Integral":[55],"Reinforcement":[56],"Learning":[57],"(IRL)":[58],"method":[59],"solve":[61],"Riccati":[64],"equations":[65],"determine":[67],"optimal":[69],"worst-case":[71],"policies":[72],"agents":[75],"by":[76],"measuring":[77],"data":[78],"along":[79],"system":[81],"trajectories.":[82]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}