{"id":"https://openalex.org/W4417438539","doi":"https://doi.org/10.1109/lcsys.2025.3645286","title":"Nash Q-Learning With Inferring Causal Signal Temporal Logic: A Study of Competitive Multi-Agent Systems","display_name":"Nash Q-Learning With Inferring Causal Signal Temporal Logic: A Study of Competitive Multi-Agent Systems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4417438539","doi":"https://doi.org/10.1109/lcsys.2025.3645286"},"language":null,"primary_location":{"id":"doi:10.1109/lcsys.2025.3645286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3645286","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-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/A5029016214","display_name":"Hadi Partovi Aria","orcid":"https://orcid.org/0000-0002-5703-1110"},"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":true,"raw_author_name":"Hadi Partovi Aria","raw_affiliation_strings":["School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ, USA","School for Engineering of Matter, Transport and Energy SEMTE, Arizona State University, Tempe, USA"],"affiliations":[{"raw_affiliation_string":"School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School for Engineering of Matter, Transport and Energy SEMTE, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013789785","display_name":"Zhe Xu","orcid":"https://orcid.org/0000-0002-0440-0912"},"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":["School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ, USA","School for Engineering of Matter, Transport and Energy SEMTE, Arizona State University, Tempe, USA"],"affiliations":[{"raw_affiliation_string":"School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School for Engineering of Matter, Transport and Energy SEMTE, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029016214"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22606707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"2867","last_page":"2872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.39100000262260437,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.39100000262260437,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.14920000731945038,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1485999971628189,"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/inference","display_name":"Inference","score":0.7098000049591064},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.6894000172615051},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6284000277519226},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5813000202178955},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5175999999046326},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.4731999933719635},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.4458000063896179},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42419999837875366}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7098000049591064},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.6894000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6460000276565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6342999935150146},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5813000202178955},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4781000018119812},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.39750000834465027},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C40149104","wikidata":"https://www.wikidata.org/wiki/Q5620977","display_name":"Factory (object-oriented programming)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C2988105877","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference system","level":5,"score":0.2702000141143799},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2025.3645286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3645286","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1547304883","https://openalex.org/W1641379095","https://openalex.org/W2099618002","https://openalex.org/W2113992026","https://openalex.org/W2524638160","https://openalex.org/W2773381986","https://openalex.org/W2807270760","https://openalex.org/W4234761190","https://openalex.org/W4400624845"],"related_works":[],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"with":[3,39,106],"temporal":[4],"logic":[5],"presents":[6,20],"unique":[7],"challenges,":[8],"particularly":[9],"in":[10,29,51],"competitive":[11,52,120],"settings":[12],"where":[13],"agents":[14,57],"pursue":[15],"conflicting":[16],"objectives.":[17],"This":[18],"paper":[19],"NASTL-CIRL":[21,92],"(Nash":[22],"Signal":[23,41],"Temporal":[24,42],"Logic":[25,43],"for":[26],"Causal":[27,40],"Inference":[28],"Reinforcement":[30],"Learning),":[31],"a":[32],"novel":[33],"approach":[34,55],"that":[35,65,101],"combines":[36],"Nash":[37,107],"Q-Learning":[38],"(Causal":[44],"STL)":[45],"inference":[46,105],"to":[47,58,84,95,111],"guide":[48],"agent":[49,67,116],"behavior":[50,68],"environments.":[53],"Our":[54,98],"enables":[56],"infer":[59],"causal":[60,103],"relationships":[61],"through":[62],"STL":[63,104],"formulas":[64],"explain":[66],"and":[69,78,114],"environmental":[70],"dynamics,":[71],"providing":[72],"strategic":[73],"advantages.":[74],"Pacman":[75],"Game":[76],"scenario":[77,81],"Factory":[79],"Assembly":[80],"are":[82],"conducted":[83],"show":[85,100],"the":[86,90],"superior":[87],"performance":[88],"of":[89],"proposed":[91],"algorithm":[93],"compared":[94],"baseline":[96],"methods.":[97],"results":[99],"integrating":[102],"equilibrium":[108],"concepts":[109],"leads":[110],"more":[112],"structured":[113],"interpretable":[115],"behaviors":[117],"while":[118],"maintaining":[119],"performance.":[121]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-17T00:00:00"}