{"id":"https://openalex.org/W2164342895","doi":"https://doi.org/10.1109/ijcnn.2004.1380091","title":"Incremental policy learning: an equilibrium selection algorithm for reinforcement learning agents with common interests","display_name":"Incremental policy learning: an equilibrium selection algorithm for reinforcement learning agents with common interests","publication_year":2005,"publication_date":"2005-04-05","ids":{"openalex":"https://openalex.org/W2164342895","doi":"https://doi.org/10.1109/ijcnn.2004.1380091","mag":"2164342895"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2004.1380091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","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/A5043661073","display_name":"Nancy Fulda","orcid":"https://orcid.org/0000-0001-9391-8301"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"N. Fulda","raw_affiliation_strings":["Department of Computer Science, Brigham Young University, Provo, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064318273","display_name":"Dan Ventura","orcid":"https://orcid.org/0000-0002-3111-2238"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Ventura","raw_affiliation_strings":["Department of Computer Science, Brigham Young University, Provo, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043661073"],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":0.9134,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8245796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1121","last_page":"1125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T11031","display_name":"Game Theory and Applications","score":0.9937999844551086,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8374501466751099},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.7074319124221802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6766574382781982},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5811466574668884},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5723385810852051},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.569014847278595},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5245147943496704},{"id":"https://openalex.org/keywords/equilibrium-selection","display_name":"Equilibrium selection","score":0.5175861120223999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4436943531036377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4434008300304413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3984985649585724},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.21297410130500793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20366516709327698},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.1668999195098877},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.08425876498222351}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8374501466751099},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.7074319124221802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6766574382781982},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5811466574668884},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5723385810852051},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.569014847278595},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5245147943496704},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.5175861120223999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4436943531036377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4434008300304413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3984985649585724},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.21297410130500793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20366516709327698},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.1668999195098877},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.08425876498222351},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn.2004.1380091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarsarchive.byu.edu:facpub-1431","is_oa":false,"landing_page_url":"https://scholarsarchive.byu.edu/facpub/432","pdf_url":null,"source":{"id":"https://openalex.org/S4377196308","display_name":"ScholarsArchive  (Brigham Young University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100005738","host_organization_name":"Brigham Young University","host_organization_lineage":["https://openalex.org/I100005738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.160.5147","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.5147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://axon.cs.byu.edu/papers/fulda.ijcnn04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W33980575","https://openalex.org/W1529602137","https://openalex.org/W1560074431","https://openalex.org/W2085366587","https://openalex.org/W2104602264","https://openalex.org/W2120846115","https://openalex.org/W2145067550","https://openalex.org/W2148962857","https://openalex.org/W6633472260","https://openalex.org/W6675811377","https://openalex.org/W6678168664","https://openalex.org/W6681342480"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576","https://openalex.org/W2272261776","https://openalex.org/W3150552942","https://openalex.org/W2129065845"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2,74],"equilibrium":[3,40,56,76],"selection":[4],"algorithm":[5,33,70,89],"for":[6,50],"reinforcement":[7],"learning":[8],"agents":[9,46],"that":[10,35,44,87],"incrementally":[11],"adjusts":[12],"the":[13,21,24,28,45,55,69,80,88,105],"probability":[14],"of":[15,23],"executing":[16],"each":[17],"action":[18],"based":[19],"on":[20],"desirability":[22],"outcome":[25],"obtained":[26],"in":[27,93,115],"last":[29],"time":[30],"step.":[31],"The":[32],"assumes":[34],"at":[36],"least":[37],"one":[38,63],"coordination":[39,67],"exists":[41],"and":[42,96],"requires":[43],"have":[47],"a":[48],"heuristic":[49,81],"determining":[51],"whether":[52],"or":[53,64],"not":[54],"was":[57],"obtained.":[58],"In":[59],"deterministic":[60],"environments":[61,95],"with":[62],"more":[65],"strict":[66],"equilibria,":[68],"learns":[71],"to":[72,99],"play":[73],"optimal":[75],"as":[77,79],"long":[78],"is":[82,90,97],"accurate.":[83],"Empirical":[84],"data":[85],"demonstrate":[86],"also":[91],"effective":[92],"stochastic":[94],"able":[98],"learn":[100],"good":[101],"joint":[102],"policies":[103],"when":[104],"heuristic's":[106],"parameters":[107],"are":[108],"estimated":[109],"during":[110],"learning,":[111],"rather":[112],"than":[113],"known":[114],"advance.":[116]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}