{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:26:19Z","timestamp":1725755179629},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T00:00:00Z","timestamp":1700438400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T00:00:00Z","timestamp":1700438400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,20]]},"DOI":"10.1109\/mhs59931.2023.10510080","type":"proceedings-article","created":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T17:27:00Z","timestamp":1714584420000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Study on High-Level Structure of cognition control construction in Exploration and Exploitation within Multi-Armed Bandit Model of Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jiaxing","family":"Tian","sequence":"first","affiliation":[{"name":"Graduate School of Science and Technology, University of Tsukuba,Empowerment Informatics"}]},{"given":"Izawa","family":"Jun","sequence":"additional","affiliation":[{"name":"Institute of Systems and Information Engineering, University of Tsukuba Tennodai 1-1-1,Tsukuba, Ibaraki,Japan,305-8573"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.6157-08.2009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/17470910903135825"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.07.002"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3758\/s13415-020-00837-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s42113-021-00112-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2230215"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195161564.003.0010"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00699"},{"key":"ref9","article-title":"Algorithms for multi-armed bandit problems[J]","author":"Kuleshov","year":"2014","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Introduction to reinforcement learning[M]","author":"Sutton","year":"1998","journal-title":"Cambridge: MIT press"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2010.5502014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhr332"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref14","article-title":"A tutorial on Bayesian optimization[J]","author":"Frazier","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/17588928.2015.1020053"}],"event":{"name":"2023 International Symposium on Micro-NanoMehatronics and Human Science (MHS)","start":{"date-parts":[[2023,11,20]]},"location":"Nagoya, Japan","end":{"date-parts":[[2023,11,22]]}},"container-title":["2023 International Symposium on Micro-NanoMehatronics and Human Science (MHS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10510017\/10510020\/10510080.pdf?arnumber=10510080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:27:14Z","timestamp":1714760834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10510080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,20]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/mhs59931.2023.10510080","relation":{},"subject":[],"published":{"date-parts":[[2023,11,20]]}}}