{"id":"https://openalex.org/W7123336725","doi":"https://doi.org/10.1109/cdc57313.2025.11312175","title":"Up Your Game: Training Games with Efficient Nash Equilibrium with Deep Learning","display_name":"Up Your Game: Training Games with Efficient Nash Equilibrium with Deep Learning","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123336725","doi":"https://doi.org/10.1109/cdc57313.2025.11312175"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th 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/A5117178088","display_name":"Ariel Kantorovich","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ariel Kantorovich","raw_affiliation_strings":["Tel Aviv University,School of Electrical and Computer Engineering,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University,School of Electrical and Computer Engineering,Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020882454","display_name":"Ilai Bistritz","orcid":"https://orcid.org/0000-0002-4120-8292"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ilai Bistritz","raw_affiliation_strings":["Tel Aviv University,School of Electrical and Computer Engineering,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University,School of Electrical and Computer Engineering,Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"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":0,"citation_normalized_percentile":{"value":0.79224241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6324","last_page":"6329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.20589999854564667,"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":0.20589999854564667,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.09220000356435776,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.07930000126361847,"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":0.754800021648407},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.5770999789237976},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5285999774932861},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.47769999504089355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4731999933719635},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4302999973297119},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.40610000491142273},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.376800000667572},{"id":"https://openalex.org/keywords/potential-game","display_name":"Potential game","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.754800021648407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085999846458435},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.5770999789237976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489000082015991},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.40610000491142273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.399399995803833},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C2778079155","wikidata":"https://www.wikidata.org/wiki/Q288500","display_name":"Potential game","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3540000021457672},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.34360000491142273},{"id":"https://openalex.org/C163630976","wikidata":"https://www.wikidata.org/wiki/Q964667","display_name":"Correlated equilibrium","level":5,"score":0.3434000015258789},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.26339998841285706},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,93,125],"consider":[1],"a":[2,10,23,28,51,77,85,96],"game":[3],"with":[4,70,81],"N":[5],"cooperative":[6],"players":[7,153],"that":[8,119],"have":[9],"global":[11,34,39,123],"objective.":[12,124],"Simple":[13],"distributed":[14],"algorithms":[15],"such":[16],"as":[17],"gradient":[18],"play":[19],"often":[20],"converge":[21],"to":[22,37,54,67,109],"Nash":[24],"equilibrium":[25],"(NE).":[26],"However,":[27],"NE":[29],"typically":[30],"suffers":[31],"from":[32,84],"poor":[33],"performance.":[35],"Converging":[36],"the":[38,56,102,105,110,113,116,122,152],"optimum":[40],"requires":[41],"explicit":[42],"communication":[43,150],"and":[44,112,136,154],"coordination.":[45],"In":[46,73],"this":[47],"paper,":[48],"we":[49,75],"propose":[50],"new":[52],"approach":[53,128,142],"improve":[55],"performance":[57,145],"at":[58],"NE.":[59,72],"Our":[60,141],"method":[61],"uses":[62],"machine":[63],"learning":[64],"offline":[65],"training":[66],"design":[68],"games":[69,80,135],"efficient":[71],"particular,":[74],"use":[76],"dataset":[78],"of":[79,132],"parameters":[82,118],"coming":[83],"certain":[86],"distribution":[87],"(e.g.,":[88],"uniformly":[89],"random":[90],"player":[91,111],"locations).":[92],"then":[94],"train":[95],"deep":[97],"neural":[98],"network":[99],"(DNN)":[100],"where":[101],"input":[103],"is":[104,115],"local":[106],"measurement":[107],"available":[108],"output":[114],"reward":[117],"best":[120],"approximate":[121],"demonstrate":[126],"our":[127],"for":[129],"two":[130],"classes":[131],"games:":[133],"energy":[134],"wireless":[137],"power":[138],"control":[139],"games.":[140],"offers":[143],"significant":[144],"boosts":[146],"while":[147],"requiring":[148],"no":[149,155],"between":[151],"complexity":[156],"increase":[157],"in":[158],"real-time.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-14T00:00:00"}