{"id":"https://openalex.org/W4205489146","doi":"https://doi.org/10.1109/cog52621.2021.9618992","title":"Playing Geister by Estimating Hidden Information with Deep Reinforcement Learning","display_name":"Playing Geister by Estimating Hidden Information with Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W4205489146","doi":"https://doi.org/10.1109/cog52621.2021.9618992"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9618992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9618992","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","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/A5051596560","display_name":"Keisuke Tomoda","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Keisuke Tomoda","raw_affiliation_strings":["Department of Computer Science, University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030198372","display_name":"Koji Hasebe","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Hasebe","raw_affiliation_strings":["Department of Computer Science, University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051596560"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18190316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"356","issue":null,"first_page":"01","last_page":"04"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9973000288009644,"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/T11197","display_name":"Digital Games and Media","score":0.9613999724388123,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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":0.9186370372772217},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.8336691856384277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7409129738807678},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.7268900871276855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5947108268737793},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5187985301017761},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.45461851358413696},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3755215108394623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14334562420845032},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.12624236941337585},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07314619421958923},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06713449954986572}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9186370372772217},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.8336691856384277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409129738807678},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.7268900871276855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5947108268737793},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5187985301017761},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.45461851358413696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3755215108394623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14334562420845032},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.12624236941337585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07314619421958923},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06713449954986572},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog52621.2021.9618992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9618992","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","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":12,"referenced_works":["https://openalex.org/W1714211023","https://openalex.org/W2103315867","https://openalex.org/W2168405694","https://openalex.org/W2257979135","https://openalex.org/W2574978968","https://openalex.org/W2902907165","https://openalex.org/W2911296969","https://openalex.org/W2960876848","https://openalex.org/W2964164283","https://openalex.org/W4297797010","https://openalex.org/W6675509861","https://openalex.org/W6696772115"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W2113798763","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W2610227658","https://openalex.org/W2900431508","https://openalex.org/W2145796981","https://openalex.org/W2050340470"],"abstract_inverted_index":{"A":[0],"number":[1],"of":[2,88,133,137],"attempts":[3],"have":[4,36],"been":[5,37],"made":[6],"to":[7,20,25,47,59,107],"solve":[8,48],"imperfect":[9,26,49,109,138],"information":[10,27,50,65,70,110,139],"games":[11,51,66,140],"using":[12,52,141],"reinforcement":[13,22,53,142],"learning.":[14,54,143],"Since":[15],"it":[16],"is":[17,58,75,91],"not":[18],"easy":[19],"apply":[21],"learning":[23,136],"directly":[24],"games,":[28],"methods,":[29],"such":[30],"as":[31],"Neural":[32],"Fictitious":[33],"Self-Play":[34],"(NFSP),":[35],"proposed.":[38],"In":[39],"this":[40,83],"study,":[41],"we":[42,123],"investigate":[43],"an":[44,108],"alternative":[45],"method":[46,106],"The":[55],"basic":[56],"idea":[57],"learn":[60],"from":[61,82,93],"self-playing":[62],"the":[63,68,72,79,85,89,94,98,104,126,134],"perfect":[64],"where":[67],"hidden":[69],"in":[71],"original":[73],"game":[74,90,111],"revealed.":[76],"Based":[77],"on":[78],"policy":[80],"obtained":[81,124],"learning,":[84],"current":[86],"state":[87],"estimated":[92],"opponent's":[95],"moves":[96],"and":[97,114],"own":[99],"best":[100],"move.":[101],"We":[102],"applied":[103],"proposed":[105],"called":[112],"Geister":[113],"evaluated":[115],"its":[116],"effectiveness":[117],"through":[118],"experiments.":[119],"As":[120],"a":[121],"result,":[122],"that":[125,132],"winning":[127],"rate":[128],"was":[129],"higher":[130],"than":[131],"direct":[135]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}