{"id":"https://openalex.org/W4403827191","doi":"https://doi.org/10.1109/tce.2024.3487141","title":"Dynamic Reinforcement Learning for Optimal Go AI Training: Adaptive Adjustment and Optimization","display_name":"Dynamic Reinforcement Learning for Optimal Go AI Training: Adaptive Adjustment and Optimization","publication_year":2024,"publication_date":"2024-10-28","ids":{"openalex":"https://openalex.org/W4403827191","doi":"https://doi.org/10.1109/tce.2024.3487141"},"language":"en","primary_location":{"id":"doi:10.1109/tce.2024.3487141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2024.3487141","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","raw_type":"journal-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":null,"display_name":"Chunjiong Zhang","orcid":"https://orcid.org/0009-0007-0213-1169"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chunjiong Zhang","raw_affiliation_strings":["Department of AI Convergence Network, Ajou University, Suwon, South Korea","Department of AI Convergence Network, Ajou University, Suwon, Korea"],"affiliations":[{"raw_affiliation_string":"Department of AI Convergence Network, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]},{"raw_affiliation_string":"Department of AI Convergence Network, Ajou University, Suwon, Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059839025","display_name":"Gaoyang Shan","orcid":"https://orcid.org/0000-0001-6763-177X"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gaoyang Shan","raw_affiliation_strings":["Department of Software and Computer Engineering, Ajou University, Suwon, South Korea","Department of Software and Computer Engineering, Ajou University, Suwon, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Software and Computer Engineering, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]},{"raw_affiliation_string":"Department of Software and Computer Engineering, Ajou University, Suwon, Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087362167","display_name":"Junghyun Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junghyun Lim","raw_affiliation_strings":["Department of AI Convergence Network, Ajou University, Suwon, South Korea","Department of AI Convergence Network, Ajou University, Suwon, Korea"],"affiliations":[{"raw_affiliation_string":"Department of AI Convergence Network, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]},{"raw_affiliation_string":"Department of AI Convergence Network, Ajou University, Suwon, Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065984213","display_name":"Byeong\u2010hee Roh","orcid":"https://orcid.org/0000-0003-2509-4210"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Hee Roh","raw_affiliation_strings":["Department of AI Convergence Network, Ajou University, Suwon, South Korea","Department of AI Convergence Network, Ajou University, Suwon, Korea"],"affiliations":[{"raw_affiliation_string":"Department of AI Convergence Network, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]},{"raw_affiliation_string":"Department of AI Convergence Network, Ajou University, Suwon, Korea","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57664883"],"apc_list":null,"apc_paid":null,"fwci":2.0356,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88946512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"71","issue":"1","first_page":"292","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.987500011920929,"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":0.987500011920929,"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":0.7639678716659546},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6293186545372009},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.567861020565033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5138673782348633},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43643930554389954},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3210831880569458},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2604012191295624}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7639678716659546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6293186545372009},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.567861020565033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138673782348633},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43643930554389954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3210831880569458},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2604012191295624},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tce.2024.3487141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2024.3487141","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2789835930","https://openalex.org/W2963698657","https://openalex.org/W2964054038","https://openalex.org/W3018036994","https://openalex.org/W3050418310","https://openalex.org/W3080611589","https://openalex.org/W3106533303","https://openalex.org/W3183431726","https://openalex.org/W4224983028","https://openalex.org/W4255900881","https://openalex.org/W4285796263","https://openalex.org/W4295046720","https://openalex.org/W4307569192","https://openalex.org/W4309663019","https://openalex.org/W4310065372","https://openalex.org/W4310705874","https://openalex.org/W4318250058","https://openalex.org/W4324028585","https://openalex.org/W4380520271","https://openalex.org/W4389083236","https://openalex.org/W4392785389","https://openalex.org/W4400138358","https://openalex.org/W4401051899","https://openalex.org/W6631190155","https://openalex.org/W6759832207","https://openalex.org/W6774804355","https://openalex.org/W6838879455","https://openalex.org/W6846896564","https://openalex.org/W6848970932","https://openalex.org/W6850137219","https://openalex.org/W6850622887","https://openalex.org/W6851841277","https://openalex.org/W6853209699","https://openalex.org/W6853300480"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Go":[0,24],"is":[1,21],"a":[2,29,64,95,135,144],"popular":[3],"strategy":[4],"game":[5],"today,":[6],"but":[7],"due":[8],"to":[9],"its":[10],"large":[11],"search":[12],"space":[13],"and":[14,34,40,52,77,89,124,143,152],"task":[15],"complexity,":[16],"ensuring":[17],"stable":[18],"AI":[19,25],"implementation":[20],"challenging.":[22],"Specifically,":[23],"training":[26,75,108,113],"requires":[27],"setting":[28],"fixed":[30],"optimal":[31],"learning":[32,58,103],"rate":[33,104,138,147],"schedule,":[35],"which":[36],"demands":[37],"significant":[38],"TPU":[39],"GPU":[41],"resources.":[42],"To":[43],"facilitate":[44],"Go-AI":[45,132],"learning,":[46],"this":[47],"research":[48],"explores":[49],"adaptive":[50],"adjustment":[51],"optimization":[53],"techniques":[54],"for":[55],"dynamic":[56,65,79,96],"reinforcement":[57],"neural":[59],"networks.":[60],"First,":[61],"we":[62,93],"introduce":[63],"batch":[66,109],"size":[67,110],"technique":[68],"that":[69,99],"adjusts":[70],"data":[71],"volume":[72],"at":[73,111,148],"each":[74],"phase":[76],"incorporates":[78],"network":[80,87,97],"structure":[81],"search,":[82],"considering":[83],"the":[84,102,107,118,131,140,149],"number":[85],"of":[86,122],"layers":[88],"residual":[90],"blocks.":[91],"Second,":[92],"propose":[94],"topology":[98],"automatically":[100],"modifies":[101],"based":[105],"on":[106],"various":[112],"phases.":[114],"Our":[115],"approach":[116],"outperforms":[117],"baseline":[119],"in":[120],"terms":[121],"stability":[123],"model":[125,133],"convergence":[126],"speed.":[127],"In":[128],"100":[129],"games,":[130],"achieved":[134],"100%":[136],"victory":[137],"below":[139],"7th":[141],"rank":[142,151],"98%":[145],"win":[146],"9th":[150],"higher.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}