{"id":"https://openalex.org/W4289874473","doi":"https://doi.org/10.1007/978-3-031-13188-2_17","title":"Specification-Guided Learning of\u00a0Nash Equilibria with\u00a0High Social Welfare","display_name":"Specification-Guided Learning of\u00a0Nash Equilibria with\u00a0High Social Welfare","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4289874473","doi":"https://doi.org/10.1007/978-3-031-13188-2_17"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-13188-2_17","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-13188-2_17","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-13188-2_17.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-13188-2_17.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055988569","display_name":"Kishor Jothimurugan","orcid":"https://orcid.org/0000-0003-1448-2947"},"institutions":[{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kishor Jothimurugan","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I922845939","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063106552","display_name":"Suguman Bansal","orcid":"https://orcid.org/0000-0002-0405-073X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suguman Bansal","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I922845939","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029243071","display_name":"Osbert Bastani","orcid":"https://orcid.org/0000-0001-9990-7566"},"institutions":[{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Osbert Bastani","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I922845939","https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065059795","display_name":"Rajeev Alur","orcid":"https://orcid.org/0000-0003-1733-7083"},"institutions":[{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajeev Alur","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I922845939","https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055988569"],"corresponding_institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":2.7383,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92000772,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"343","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9760000109672546,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9570000171661377,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8315122723579407},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.829703688621521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.656261682510376},{"id":"https://openalex.org/keywords/welfare","display_name":"Welfare","score":0.5932595133781433},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5803027749061584},{"id":"https://openalex.org/keywords/social-welfare","display_name":"Social Welfare","score":0.5658770203590393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42839688062667847},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.4066859483718872},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3509749472141266},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3486488461494446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18446600437164307},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.17465361952781677},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09580865502357483}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8315122723579407},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.829703688621521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656261682510376},{"id":"https://openalex.org/C100243477","wikidata":"https://www.wikidata.org/wiki/Q12002092","display_name":"Welfare","level":2,"score":0.5932595133781433},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5803027749061584},{"id":"https://openalex.org/C536738050","wikidata":"https://www.wikidata.org/wiki/Q3249071","display_name":"Social Welfare","level":2,"score":0.5658770203590393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42839688062667847},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.4066859483718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3509749472141266},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3486488461494446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18446600437164307},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.17465361952781677},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09580865502357483},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-13188-2_17","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-13188-2_17","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-13188-2_17.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-13188-2_17","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-13188-2_17","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-13188-2_17.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G1633690903","display_name":null,"funder_award_id":"00014-20","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2336166159","display_name":null,"funder_award_id":"4-20-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5524522455","display_name":null,"funder_award_id":"DARPA","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6074853558","display_name":null,"funder_award_id":"W911NF-20-1-0080","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6925521478","display_name":null,"funder_award_id":"N00014-20-1-2115","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7034037648","display_name":null,"funder_award_id":"4-20-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7698193007","display_name":null,"funder_award_id":"2030859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289874473.pdf","grobid_xml":"https://content.openalex.org/works/W4289874473.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W190698121","https://openalex.org/W1496672808","https://openalex.org/W1513468570","https://openalex.org/W1542941925","https://openalex.org/W1565676156","https://openalex.org/W1583837637","https://openalex.org/W2575731723","https://openalex.org/W2604738573","https://openalex.org/W2977509914","https://openalex.org/W3042980517","https://openalex.org/W3208792968","https://openalex.org/W4205559356","https://openalex.org/W6636134071"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4319083788","https://openalex.org/W4281686840","https://openalex.org/W4289874473"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"learning":[2,29],"has":[3],"been":[4],"shown":[5],"to":[6,74,123],"be":[7],"an":[8,80],"effective":[9],"strategy":[10],"for":[11,15,31],"automatically":[12],"training":[13,32],"policies":[14,34,73,93,113],"challenging":[16],"control":[17],"problems.":[18],"Focusing":[19],"on":[20],"non-cooperative":[21],"multi-agent":[22],"systems,":[23],"we":[24],"propose":[25],"a":[26,37,95],"novel":[27],"reinforcement":[28],"framework":[30],"joint":[33],"that":[35,54,77,97,108],"form":[36],"Nash":[38,125],"equilibrium.":[39],"In":[40],"our":[41,69,109],"approach,":[42],"rather":[43],"than":[44],"providing":[45],"low-level":[46],"reward":[47],"functions,":[48],"the":[49,56,64,67],"user":[50],"provides":[51],"high-level":[52],"specifications":[53],"encode":[55],"objective":[57],"of":[58,66],"each":[59],"agent.":[60],"Then,":[61],"guided":[62],"by":[63],"structure":[65],"specifications,":[68],"algorithm":[70,110],"searches":[71],"over":[72],"identify":[75],"one":[76],"provably":[78],"forms":[79],"$$\\epsilon":[81],"$$":[82],"<mml:math":[83],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mi>\u03f5</mml:mi></mml:math>":[84],"-Nash":[85],"equilibrium":[86,112],"(with":[87],"high":[88,115],"probability).":[89],"Importantly,":[90],"it":[91],"prioritizes":[92],"in":[94],"way":[96],"maximizes":[98],"social":[99,116,133],"welfare":[100],"across":[101],"all":[102],"agents.":[103],"Our":[104],"empirical":[105],"evaluation":[106],"demonstrates":[107],"computes":[111],"with":[114,130],"welfare,":[117],"whereas":[118],"state-of-the-art":[119],"baselines":[120],"either":[121],"fail":[122],"compute":[124,128],"equilibria":[126],"or":[127],"ones":[129],"comparatively":[131],"lower":[132],"welfare.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}