{"id":"https://openalex.org/W4407950072","doi":"https://doi.org/10.1109/cdc56724.2024.10886810","title":"Generalized Individual Q-learning for Polymatrix Games with Partial Observations","display_name":"Generalized Individual Q-learning for Polymatrix Games with Partial Observations","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407950072","doi":"https://doi.org/10.1109/cdc56724.2024.10886810"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd 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/A5093875939","display_name":"Ahmed Said Donmez","orcid":null},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ahmed Said Donmez","raw_affiliation_strings":["Bilkent University,Department of Electrical and Electronics Engineering,Ankara,Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilkent University,Department of Electrical and Electronics Engineering,Ankara,Türkiye","institution_ids":["https://openalex.org/I168864056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081851582","display_name":"Muhammed O. Sayin","orcid":"https://orcid.org/0000-0001-5779-3986"},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Muhammed O. Sayin","raw_affiliation_strings":["Bilkent University,Department of Electrical and Electronics Engineering,Ankara,Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilkent University,Department of Electrical and Electronics Engineering,Ankara,Türkiye","institution_ids":["https://openalex.org/I168864056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168864056"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29403862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3209","last_page":"3214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6818000078201294,"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":0.6818000078201294,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.5810999870300293,"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":0.5745999813079834,"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/computer-science","display_name":"Computer science","score":0.5914465188980103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37050962448120117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5914465188980103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37050962448120117}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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":14,"referenced_works":["https://openalex.org/W1491706803","https://openalex.org/W1964757264","https://openalex.org/W1967250398","https://openalex.org/W2060341614","https://openalex.org/W2096348520","https://openalex.org/W2117255278","https://openalex.org/W2135071748","https://openalex.org/W2176451521","https://openalex.org/W2264897026","https://openalex.org/W2288719682","https://openalex.org/W4244096180","https://openalex.org/W6736534893","https://openalex.org/W6854882467","https://openalex.org/W6857830505"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0,45],"paper":[1],"addresses":[2],"the":[3,24,36,72,76,96],"challenge":[4],"of":[5,39],"limited":[6],"observations":[7],"in":[8,64,98],"non-cooperative":[9],"multi-agent":[10,65],"systems":[11],"where":[12],"agents":[13],"can":[14],"have":[15],"partial":[16],"access":[17,48,88],"to":[18,49,60,75,89,102],"other":[19],"agents\u2019":[20],"actions.":[21],"We":[22,93],"present":[23],"generalized":[25],"individual":[26,82],"Q-learning":[27,83],"dynamics":[28,73],"that":[29],"combine":[30],"belief-based":[31],"and":[32,67,81,86],"payoff-based":[33],"learning":[34],"for":[35],"networked":[37],"interconnections":[38],"more":[40],"than":[41],"two":[42],"self-interested":[43],"agents.":[44],"approach":[46],"leverages":[47],"opponents\u2019":[50,104],"actions":[51,105],"whenever":[52],"possible,":[53],"demonstrably":[54],"achieving":[55],"a":[56],"faster":[57],"(guaranteed)":[58],"convergence":[59,99],"quantal":[61],"response":[62],"equilibrium":[63],"zero-sum":[66],"potential":[68],"polymatrix":[69],"games.":[70],"Notably,":[71],"reduce":[74],"well-studied":[77],"smoothed":[78],"fictitious":[79],"play":[80],"under":[84],"full":[85],"no":[87],"opponent":[90],"actions,":[91],"respectively.":[92],"further":[94],"quantify":[95],"improvement":[97],"rate":[100],"due":[101],"observing":[103],"through":[106],"numerical":[107],"simulations.":[108]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}