{"id":"https://openalex.org/W4220970626","doi":"https://doi.org/10.23919/icact53585.2022.9728964","title":"The Method of Learning Personal Preference with Reinforcement Learning","display_name":"The Method of Learning Personal Preference with Reinforcement Learning","publication_year":2022,"publication_date":"2022-02-13","ids":{"openalex":"https://openalex.org/W4220970626","doi":"https://doi.org/10.23919/icact53585.2022.9728964"},"language":"en","primary_location":{"id":"doi:10.23919/icact53585.2022.9728964","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact53585.2022.9728964","pdf_url":null,"source":{"id":"https://openalex.org/S4363608017","display_name":"2022 24th International Conference on Advanced Communication Technology (ICACT)","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":"2022 24th International Conference on Advanced Communication Technology (ICACT)","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/A5103016097","display_name":"Yong\u2010Hee Park","orcid":null},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yong Hee Park","raw_affiliation_strings":["Chungbuk National University,Information & communication Engineering,Chungcheongbuk-do,Korea"],"affiliations":[{"raw_affiliation_string":"Chungbuk National University,Information & communication Engineering,Chungcheongbuk-do,Korea","institution_ids":["https://openalex.org/I163753206"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073051296","display_name":"Won Seok Choi","orcid":"https://orcid.org/0000-0002-4203-0457"},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won Seok Choi","raw_affiliation_strings":["Chungbuk National University,Information & communication Engineering,Chungcheongbuk-do,Korea"],"affiliations":[{"raw_affiliation_string":"Chungbuk National University,Information & communication Engineering,Chungcheongbuk-do,Korea","institution_ids":["https://openalex.org/I163753206"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026721662","display_name":"Seong Gon Choi","orcid":"https://orcid.org/0000-0002-5326-8321"},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong Gon Choi","raw_affiliation_strings":["Chungbuk National University,Information & communication Engineering,Chungcheongbuk-do,Korea"],"affiliations":[{"raw_affiliation_string":"Chungbuk National University,Information & communication Engineering,Chungcheongbuk-do,Korea","institution_ids":["https://openalex.org/I163753206"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103016097"],"corresponding_institution_ids":["https://openalex.org/I163753206"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0150299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.8259000182151794,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.8259000182151794,"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/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.8154000043869019,"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/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.809499979019165,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7395076751708984},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7315313816070557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5904524326324463},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5488078594207764},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.4538317322731018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3945503830909729},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16552987694740295},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10482311248779297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09396356344223022},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08420717716217041}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7395076751708984},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7315313816070557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5904524326324463},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5488078594207764},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.4538317322731018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3945503830909729},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16552987694740295},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10482311248779297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09396356344223022},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08420717716217041}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/icact53585.2022.9728964","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact53585.2022.9728964","pdf_url":null,"source":{"id":"https://openalex.org/S4363608017","display_name":"2022 24th International Conference on Advanced Communication Technology (ICACT)","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":"2022 24th International Conference on Advanced Communication Technology (ICACT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2039100388","https://openalex.org/W2076337359","https://openalex.org/W2130711276","https://openalex.org/W2170430646","https://openalex.org/W2618160968","https://openalex.org/W2794190393","https://openalex.org/W2944766483","https://openalex.org/W2979039524","https://openalex.org/W3027718154","https://openalex.org/W3118466402","https://openalex.org/W3125510825","https://openalex.org/W3156834793","https://openalex.org/W3161100355","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2937325523","https://openalex.org/W4205377104","https://openalex.org/W257970033","https://openalex.org/W1994181006","https://openalex.org/W2911102221","https://openalex.org/W4285602503","https://openalex.org/W2943672508","https://openalex.org/W4383737174","https://openalex.org/W4320918405","https://openalex.org/W4281387587"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,18,61],"method":[3,19,77],"of":[4,41],"learning":[5,25,42],"personal":[6,15,38],"preference":[7,16],"using":[8,20,75],"Reinforcement":[9],"Learning":[10],"(RL).":[11],"Existing":[12],"research":[13],"on":[14],"is":[17,44],"machine":[21],"learning,":[22],"and":[23,65,73],"the":[24],"results":[26,69],"are":[27],"simply":[28],"related":[29],"to":[30,35,51],"input":[31],"data.":[32],"In":[33],"order":[34],"better":[36],"learn":[37],"preference,":[39],"evaluation":[40],"result":[43],"also":[45],"important.":[46],"Therefore,":[47],"we":[48,59],"use":[49],"RL":[50],"calculate":[52],"reward":[53,74],"for":[54],"learners\u2019":[55],"choice.":[56],"For":[57],"this,":[58],"design":[60],"model":[62],"that":[63],"calculates":[64],"evaluates":[66],"reward.":[67],"The":[68],"show":[70],"learned":[71],"policy":[72],"proposed":[76],"in":[78],"environment.":[79]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}