{"id":"https://openalex.org/W4386159807","doi":"https://doi.org/10.1109/icarm58088.2023.10218910","title":"Nash Equilibrium Solution Based on Safety-Guarding Reinforcement Learning in Nonzero-Sum Game","display_name":"Nash Equilibrium Solution Based on Safety-Guarding Reinforcement Learning in Nonzero-Sum Game","publication_year":2023,"publication_date":"2023-07-08","ids":{"openalex":"https://openalex.org/W4386159807","doi":"https://doi.org/10.1109/icarm58088.2023.10218910"},"language":"en","primary_location":{"id":"doi:10.1109/icarm58088.2023.10218910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm58088.2023.10218910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","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/A5072704732","display_name":"Junkai Tan","orcid":"https://orcid.org/0009-0000-2323-3892"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junkai Tan","raw_affiliation_strings":["Xi'an Jiaotong University,Shaanxi Key Laboratory of Smart Grid,Xi'an,China,710049","State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,Shaanxi Key Laboratory of Smart Grid,Xi'an,China,710049","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003247946","display_name":"Shuangsi Xue","orcid":"https://orcid.org/0000-0002-7623-0051"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangsi Xue","raw_affiliation_strings":["Xi'an Jiaotong University,Shaanxi Key Laboratory of Smart Grid,Xi'an,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,Shaanxi Key Laboratory of Smart Grid,Xi'an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084856540","display_name":"Hui Cao","orcid":"https://orcid.org/0000-0003-3301-2713"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Cao","raw_affiliation_strings":["Xi'an Jiaotong University,Shaanxi Key Laboratory of Smart Grid,Xi'an,China,710049","State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,Shaanxi Key Laboratory of Smart Grid,Xi'an,China,710049","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100607146","display_name":"Huan Li","orcid":"https://orcid.org/0009-0002-3838-0267"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Li","raw_affiliation_strings":["Xi'an Jiaotong University,Shaanxi Key Laboratory of Smart Grid,Xi'an,China,710049","State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,Shaanxi Key Laboratory of Smart Grid,Xi'an,China,710049","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.9444,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6979264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"630","last_page":"635"},"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":0.9891999959945679,"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/T12047","display_name":"Viral Infections and Vectors","score":0.967199981212616,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8856468200683594},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7873928546905518},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6428146362304688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.591996431350708},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.5756990909576416},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5468759536743164},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.5304621458053589},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.49868273735046387},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.43442755937576294},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.41483867168426514},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.413901150226593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2694021761417389},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.21835899353027344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21708962321281433}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8856468200683594},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7873928546905518},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6428146362304688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.591996431350708},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.5756990909576416},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5468759536743164},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.5304621458053589},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.49868273735046387},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.43442755937576294},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.41483867168426514},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.413901150226593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2694021761417389},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.21835899353027344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21708962321281433},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/icarm58088.2023.10218910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm58088.2023.10218910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","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":25,"referenced_works":["https://openalex.org/W1793264465","https://openalex.org/W1914756871","https://openalex.org/W1977671496","https://openalex.org/W1983523797","https://openalex.org/W2019338681","https://openalex.org/W2032631296","https://openalex.org/W2085194340","https://openalex.org/W2108286682","https://openalex.org/W2312229020","https://openalex.org/W2579592432","https://openalex.org/W2727279496","https://openalex.org/W2971473345","https://openalex.org/W2996568167","https://openalex.org/W3009484445","https://openalex.org/W3013559981","https://openalex.org/W3046220573","https://openalex.org/W3048735518","https://openalex.org/W3114263192","https://openalex.org/W3154507809","https://openalex.org/W3204849641","https://openalex.org/W3207311111","https://openalex.org/W4200325667","https://openalex.org/W4285206367","https://openalex.org/W4308345587","https://openalex.org/W4321366636"],"related_works":["https://openalex.org/W2236801283","https://openalex.org/W2728657731","https://openalex.org/W1853631319","https://openalex.org/W2092374696","https://openalex.org/W2481143976","https://openalex.org/W2803932348","https://openalex.org/W3207342620","https://openalex.org/W2607684552","https://openalex.org/W2013767790","https://openalex.org/W4241870466"],"abstract_inverted_index":{"In":[0,62],"this":[1],"paper,":[2],"a":[3,31,44,69,84],"safety-guarding":[4],"controller":[5,19],"is":[6,20,48,72,88],"introduced":[7],"to":[8,22,64],"keep":[9],"the":[10,24,39,59,66,78,81],"safety":[11],"of":[12,41,80],"exploration":[13],"in":[14,58],"constrained":[15],"state":[16],"space.":[17],"The":[18],"utilized":[21,73],"obtain":[23],"nonzero-sum":[25,86],"game":[26,87],"Nash":[27],"equilibrium":[28],"solution":[29],"via":[30],"model-based":[32],"reinforcement":[33],"learning":[34,46,60],"architecture.":[35],"To":[36,76],"deal":[37],"with":[38],"uncertainty":[40],"persistent":[42],"excitation,":[43],"concurrent":[45],"approach":[47],"applied":[49],"and":[50,53],"both":[51,91],"historical":[52],"transient":[54],"data":[55],"are":[56],"employed":[57],"process.":[61],"order":[63],"reduce":[65],"computational":[67],"load,":[68],"single-critic":[70],"network":[71],"for":[74],"approximation.":[75],"demonstrate":[77],"effectiveness":[79],"proposed":[82],"method,":[83],"two-player":[85],"developed,":[89],"toward":[90],"convex/non-convex":[92],"safe":[93],"state-space":[94],"constraints.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}