{"id":"https://openalex.org/W2344546574","doi":"https://doi.org/10.5220/0005711000470055","title":"Adaptive Two-stage Learning Algorithm for Repeated Games","display_name":"Adaptive Two-stage Learning Algorithm for Repeated Games","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2344546574","doi":"https://doi.org/10.5220/0005711000470055","mag":"2344546574"},"language":"en","primary_location":{"id":"doi:10.5220/0005711000470055","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005711000470055","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005711000470055","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062207773","display_name":"Wataru Fujita","orcid":"https://orcid.org/0000-0003-4124-7264"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wataru Fujita","raw_affiliation_strings":["Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066183149","display_name":"Koichi Moriyama","orcid":"https://orcid.org/0000-0003-1735-1862"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Moriyama","raw_affiliation_strings":["Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075653507","display_name":"Ken\u2013ichi Fukui","orcid":"https://orcid.org/0000-0002-2451-1919"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ken-ichi Fukui","raw_affiliation_strings":["Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002214819","display_name":"Masayuki Numao","orcid":"https://orcid.org/0000-0002-4890-1970"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Numao","raw_affiliation_strings":["Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"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":0.01895834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.8921999931335449,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.8921999931335449,"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":0.870199978351593,"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/T11674","display_name":"Sports Analytics and Performance","score":0.8618000149726868,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.811165452003479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7760453224182129},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6618391871452332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49706724286079407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46819719672203064},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.445221871137619},{"id":"https://openalex.org/keywords/combinatorial-game-theory","display_name":"Combinatorial game theory","score":0.4412403404712677},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.41587454080581665},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3704591393470764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15218141674995422},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.08590862154960632}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.811165452003479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760453224182129},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6618391871452332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49706724286079407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46819719672203064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.445221871137619},{"id":"https://openalex.org/C102234262","wikidata":"https://www.wikidata.org/wiki/Q1320931","display_name":"Combinatorial game theory","level":4,"score":0.4412403404712677},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.41587454080581665},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3704591393470764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15218141674995422},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.08590862154960632}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0005711000470055","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005711000470055","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0005711000470055","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005711000470055","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2276575217","https://openalex.org/W190963404","https://openalex.org/W2141950114","https://openalex.org/W3139383627","https://openalex.org/W2039104542","https://openalex.org/W2134321370","https://openalex.org/W4372324527","https://openalex.org/W2071306797","https://openalex.org/W26097285","https://openalex.org/W4377081010"],"abstract_inverted_index":{"In":[0,61],"our":[1,96,103,120],"society,":[2],"people":[3,22],"engage":[4],"in":[5,46,75,89,101,111,134],"a":[6,19,37,56],"variety":[7],"of":[8,39,42,59,95,109],"interactions.":[9,60],"To":[10],"analyze":[11],"such":[12],"interactions,":[13],"we":[14,64],"consider":[15],"these":[16],"interactions":[17],"as":[18,23],"game":[20],"and":[21,72,92,113,129],"agents":[24,105],"equipped":[25],"with":[26,36,114],"reinforcement":[27],"learning":[28,31],"algorithms.":[29],"Reinforcement":[30],"algorithms":[32,50,85,128],"are":[33,87],"widely":[34],"studied":[35],"goal":[38],"identifying":[40],"strategies":[41],"gaining":[43],"large":[44,57,132],"payoffs":[45,74,133],"games;":[47],"however,":[48],"existing":[49,127],"learn":[51],"slowly":[52],"because":[53],"they":[54],"require":[55],"number":[58],"this":[62],"work,":[63],"constructed":[65],"an":[66],"algorithm":[67,81,122],"that":[68,86,119],"both":[69],"learns":[70],"quickly":[71,125],"maximizes":[73],"various":[76],"repeated":[77],"games.":[78,136],"Our":[79],"proposed":[80,104,121],"combines":[82],"two":[83],"different":[84],"used":[88],"the":[90],"early":[91],"later":[93],"stages":[94],"algorithm.":[97],"We":[98],"conducted":[99],"experiments":[100],"which":[102],"played":[106],"ten":[107],"kinds":[108],"games":[110],"self-play":[112],"other":[115],"agents.":[116],"Results":[117],"showed":[118],"learned":[123],"more":[124],"than":[126],"gained":[130],"sufficiently":[131],"nine":[135]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}