{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:10:41Z","timestamp":1776053441069,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Brain Korea 21 (BK21) FOUR Program of the National Research Foundation of Korea funded by the Ministry of Education","award":["NRF5199991514504"],"award-info":[{"award-number":["NRF5199991514504"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tce.2024.3487141","type":"journal-article","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T17:35:24Z","timestamp":1730136924000},"page":"292-302","source":"Crossref","is-referenced-by-count":7,"title":["Dynamic Reinforcement Learning for Optimal Go AI Training: Adaptive Adjustment and Optimization"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0213-1169","authenticated-orcid":false,"given":"Chunjiong","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of AI Convergence Network, Ajou University, Suwon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6763-177X","authenticated-orcid":false,"given":"Gaoyang","family":"Shan","sequence":"additional","affiliation":[{"name":"Department of Software and Computer Engineering, Ajou University, Suwon, South Korea"}]},{"given":"Junghyun","family":"Lim","sequence":"additional","affiliation":[{"name":"Department of AI Convergence Network, Ajou University, Suwon, South Korea"}]},{"given":"Byeong-Hee","family":"Roh","sequence":"additional","affiliation":[{"name":"Department of AI Convergence Network, Ajou University, Suwon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"goreviewpartner","year":"2023"},{"key":"ref2","volume-title":"yikeweiqi","year":"2023"},{"key":"ref3","first-page":"772","article-title":"UnderGrad: A universal black-box optimization method with almost dimension-free convergence rate guarantees","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Antonakopoulos"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2020.3037065"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2022.3205376"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2022.100422"},{"key":"ref7","first-page":"7449","article-title":"Learning-rate-free learning by d-adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Defazio"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.53106\/199115992024063503009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade9097"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3240249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683076"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","first-page":"14465","article-title":"DoG is SGD\u2019s best friend: A parameter-free dynamic step size schedule","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ivgi"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-3245-6_9"},{"key":"ref16","first-page":"6748","article-title":"DoWG unleashed: An efficient universal parameter-free gradient descent method","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khaled"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref18","first-page":"5381","article-title":"A unified theory of decentralized SGD with changing topology and local updates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koloskova"},{"key":"ref19","first-page":"1","article-title":"Pgx: Hardware-accelerated parallel game simulators for reinforcement learning","volume-title":"Proc. 37th Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Koyamada"},{"key":"ref20","first-page":"36944","article-title":"Trajectory of mini-batch momentum: Batch size saturation and convergence in high dimensions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref21","first-page":"1","article-title":"Convex and non-convex optimization under generalized smoothness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li"},{"key":"ref22","volume-title":"Leela zero","author":"Pascutto"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app10175792"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-020-02646-9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.measen.2022.100602"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5829\/IJE.2024.37.02B.07"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3279381"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2214840120"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s44223-023-00046-9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10228-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.4135\/9781412983907.n1717"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105506"},{"key":"ref35","article-title":"Accelerating self-play learning in Go","author":"Wu","year":"2019","journal-title":"arXiv:1902.10565"},{"key":"ref36","first-page":"37787","article-title":"On the training instability of shuffling SGD with batch normalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-018-3158-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01138"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11038962\/10737295.pdf?arnumber=10737295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:38:27Z","timestamp":1750268307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10737295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2024.3487141","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}