{"id":"https://openalex.org/W4383108404","doi":"https://doi.org/10.1109/icra48891.2023.10160219","title":"Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games","display_name":"Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108404","doi":"https://doi.org/10.1109/icra48891.2023.10160219"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160219","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10160219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5070346662","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-0096-7073"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Arizona State University,Department of Mechanical and Aerospace Engineering,Tempe,AZ,USA,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Department of Mechanical and Aerospace Engineering,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060318659","display_name":"Mukesh Ghimire","orcid":"https://orcid.org/0009-0005-5660-5054"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mukesh Ghimire","raw_affiliation_strings":["Arizona State University,Department of Mechanical and Aerospace Engineering,Tempe,AZ,USA,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Department of Mechanical and Aerospace Engineering,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453347","display_name":"Wenlong Zhang","orcid":"https://orcid.org/0000-0002-4046-2213"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenlong Zhang","raw_affiliation_strings":["Polytechnic School, Ira A. Fulton Schools of Engineering, Arizona State University,Mesa,AZ,USA,85212"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic School, Ira A. Fulton Schools of Engineering, Arizona State University,Mesa,AZ,USA,85212","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101459711","display_name":"Zhe Xu","orcid":"https://orcid.org/0000-0001-5157-570X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Xu","raw_affiliation_strings":["Arizona State University,Department of Mechanical and Aerospace Engineering,Tempe,AZ,USA,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Department of Mechanical and Aerospace Engineering,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812349","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0003-2306-5993"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Arizona State University,Department of Mechanical and Aerospace Engineering,Tempe,AZ,USA,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Department of Mechanical and Aerospace Engineering,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"3022","last_page":"3028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9786999821662903,"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":0.9545000195503235,"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/nash-equilibrium","display_name":"Nash equilibrium","score":0.6388513445854187},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6042741537094116},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5623396039009094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5611955523490906},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5437785387039185},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5244298577308655},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48536932468414307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35581228137016296},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32996666431427},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07225486636161804}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6388513445854187},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6042741537094116},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5623396039009094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5611955523490906},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5437785387039185},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5244298577308655},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48536932468414307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35581228137016296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32996666431427},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07225486636161804}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160219","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10160219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1741859010","display_name":"NRI: FND: Scalable and Customizable Intent Inference and Motion Planning for Socially-Adept Autonomous Vehicles","funder_award_id":"1925403","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W315739085","https://openalex.org/W1515852644","https://openalex.org/W2055300044","https://openalex.org/W2087599797","https://openalex.org/W2091510786","https://openalex.org/W2103315867","https://openalex.org/W2113108728","https://openalex.org/W2116364955","https://openalex.org/W2248846161","https://openalex.org/W2588978360","https://openalex.org/W2800727637","https://openalex.org/W2803629276","https://openalex.org/W2891385160","https://openalex.org/W2899507754","https://openalex.org/W2948551291","https://openalex.org/W2953931148","https://openalex.org/W2962727772","https://openalex.org/W2963146412","https://openalex.org/W2972723147","https://openalex.org/W2990116160","https://openalex.org/W2990653181","https://openalex.org/W3006784013","https://openalex.org/W3027682703","https://openalex.org/W3039086578","https://openalex.org/W3044994704","https://openalex.org/W3089576059","https://openalex.org/W3093786597","https://openalex.org/W3104441224","https://openalex.org/W3205025130","https://openalex.org/W3206190169","https://openalex.org/W4200574011","https://openalex.org/W4239369248","https://openalex.org/W4284881952","https://openalex.org/W4288083537","https://openalex.org/W4295150809","https://openalex.org/W4310705874","https://openalex.org/W6638908295","https://openalex.org/W6675509861","https://openalex.org/W6691217529","https://openalex.org/W6744562401","https://openalex.org/W6781244629","https://openalex.org/W6996504251"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W4296209631","https://openalex.org/W2334570605","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W3149091143"],"abstract_inverted_index":{"Finding":[0],"Nash":[1,77],"equilibrial":[2],"policies":[3],"for":[4,185],"two-player":[5],"differential":[6],"games":[7],"requires":[8],"solving":[9],"Hamilton-Jacobi-Isaacs":[10],"(HJI)":[11],"PDEs.":[12],"Self-supervised":[13],"learning":[14,186],"has":[15],"been":[16],"used":[17],"to":[18,34,40,45,67,163,181],"approximate":[19],"solutions":[20,38,66,102],"of":[21,28,49,90,138],"such":[22],"PDEs":[23,187],"while":[24],"circumventing":[25],"the":[26,50,80,104,135,141,149,166,176],"curse":[27],"dimensionality.":[29],"However,":[30],"this":[31,68],"method":[32,72,86,143],"fails":[33,162],"learn":[35],"discontinuous":[36],"PDE":[37],"due":[39],"its":[41,189],"sampling":[42],"nature,":[43],"leading":[44],"poor":[46],"safety":[47,108,146],"performance":[48,109,147],"resulting":[51,105],"controllers":[52],"in":[53,110,165],"robotics":[54],"applications":[55],"when":[56],"player":[57],"rewards":[58],"are":[59,92],"discontinuous.":[60],"This":[61],"paper":[62],"investigates":[63],"two":[64,111],"potential":[65],"problem:":[69],"a":[70,84,88,95],"hybrid":[71,142],"that":[73,125,175],"leverages":[74],"both":[75],"supervised":[76],"equilibria":[78],"and":[79,83,107,118,131,134,152,188],"HJI":[81],"PDE,":[82],"value-hardening":[85],"where":[87],"sequence":[89],"HJIs":[91],"solved":[93],"with":[94,116,126],"gradually":[96],"hardening":[97,154,161],"reward.":[98],"We":[99],"compare":[100],"these":[101],"using":[103],"generalization":[106],"vehicle":[112],"interaction":[113],"simulation":[114],"studies":[115],"5D":[117],"9D":[119],"state":[120],"spaces,":[121],"respectively.":[122],"Results":[123],"show":[124,174],"informative":[127,170],"supervision":[128],"(e.g.,":[129],"collision":[130],"near-collision":[132],"demonstrations)":[133],"low":[136],"cost":[137],"self-supervised":[139],"learning,":[140],"achieves":[144],"better":[145],"than":[148],"supervised,":[150],"self-supervised,":[151],"value":[153],"approaches":[155],"on":[156],"equal":[157],"computational":[158],"budget.":[159],"Value":[160],"generalize":[164],"higher-dimensional":[167],"case":[168,193],"without":[169],"supervision.":[171],"Lastly,":[172],"we":[173],"neural":[177],"activation":[178],"function":[179],"needs":[180],"be":[182,192],"continuously":[183],"differentiable":[184],"choice":[190],"can":[191],"dependent.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}