{"id":"https://openalex.org/W4400525083","doi":"https://doi.org/10.1109/tg.2024.3424668","title":"More Human-Like Gameplay by Blending Policies From Supervised and Reinforcement Learning","display_name":"More Human-Like Gameplay by Blending Policies From Supervised and Reinforcement Learning","publication_year":2024,"publication_date":"2024-07-11","ids":{"openalex":"https://openalex.org/W4400525083","doi":"https://doi.org/10.1109/tg.2024.3424668"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2024.3424668","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tg.2024.3424668","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tg.2024.3424668","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021937418","display_name":"Tatsuyoshi Ogawa","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tatsuyoshi Ogawa","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056723326","display_name":"Chu-Hsuan Hsueh","orcid":"https://orcid.org/0000-0001-8888-3116"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chu-Hsuan Hsueh","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105422798","display_name":"Kokolo Ikeda","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kokolo Ikeda","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021937418"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.6879,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74254555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"16","issue":"4","first_page":"831","last_page":"843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8263999819755554,"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":0.8263999819755554,"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/T12290","display_name":"Human Motion and Animation","score":0.8241000175476074,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.7667999863624573,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7678384780883789},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6265214681625366},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.6215000748634338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5205329656600952},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4915948808193207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2564128041267395},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24938708543777466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1907605230808258},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11897340416908264}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7678384780883789},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6265214681625366},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6215000748634338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5205329656600952},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4915948808193207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2564128041267395},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24938708543777466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1907605230808258},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11897340416908264}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tg.2024.3424668","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tg.2024.3424668","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01333:0006991748","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/20010","pdf_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/20010/1/T-IKEDA-K-0930-2.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/tg.2024.3424668","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tg.2024.3424668","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W158031290","https://openalex.org/W192262237","https://openalex.org/W1500868819","https://openalex.org/W2067279781","https://openalex.org/W2165999534","https://openalex.org/W2174702525","https://openalex.org/W2194775991","https://openalex.org/W2219479003","https://openalex.org/W2589376635","https://openalex.org/W2792919371","https://openalex.org/W2902907165","https://openalex.org/W2913201078","https://openalex.org/W3033620876","https://openalex.org/W4254114471","https://openalex.org/W4323240466","https://openalex.org/W4390841069","https://openalex.org/W6718092244","https://openalex.org/W6805718147"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Modeling":[0],"human":[1,55],"players'":[2],"behaviors":[3],"in":[4,76],"games":[5,61],"is":[6,44,65],"a":[7,69,85,129],"key":[8],"challenge":[9],"for":[10,58,89],"making":[11],"natural":[12],"computer":[13],"players,":[14],"evaluating":[15],"games,":[16,151],"and":[17,36,126,147,167],"generating":[18],"content.":[19],"To":[20],"achieve":[21],"better":[22,185],"humancomputer":[23],"interaction,":[24],"researchers":[25],"have":[26],"tried":[27,190],"various":[28],"methods":[29],"to":[30,53,67,87,164,191],"create":[31],"human-like":[32],"AI.":[33],"In":[34,176],"chess":[35,125],"Go,":[37],"supervised":[38,82,94,120],"learning":[39,95,104,121],"with":[40,100,128,144],"deep":[41],"neural":[42],"networks":[43],"known":[45],"as":[46],"one":[47],"of":[48,72,80,92,132,150,160],"the":[49,81,90,93,111,116,153,158,161,165,169,172,181,193],"most":[50],"effective":[51,143],"ways":[52],"predict":[54],"moves.":[56],"However,":[57],"many":[59],"other":[60],"(e.g.,":[62],"Shogi),":[63],"it":[64,99],"hard":[66],"collect":[68],"similar":[70,137],"amount":[71],"game":[73,133],"records,":[74],"resulting":[75],"poor":[77],"move-matching":[78,117,173,194],"accuracy":[79,118,174],"learning.We":[83],"propose":[84],"method":[86,113,141],"compensate":[88],"weakness":[91],"policy":[96],"by":[97],"Blending":[98],"an":[101],"AlphaZerolike":[102],"reinforcement":[103],"policy.":[105],"Experiments":[106,123],"on":[107,124],"Shogi":[108],"showed":[109,136,179],"that":[110,180,189],"Blend":[112,140,162,182],"significantly":[114],"improved":[115],"over":[119],"models.":[122],"Go":[127],"limited":[130],"number":[131],"records":[134],"also":[135],"results.":[138],"The":[139],"was":[142],"both":[145],"medium":[146,154],"large":[148],"numbers":[149],"particularly":[152],"case.":[155],"We":[156],"confirmed":[157],"robustness":[159],"model":[163,183],"parameter":[166],"discussed":[168],"mechanism":[170],"why":[171],"improves.":[175],"addition,":[177],"we":[178],"performed":[184],"than":[186],"existing":[187],"work":[188],"improve":[192],"accuracy.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}