{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T16:20:18Z","timestamp":1726849218200},"reference-count":7,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":151,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2017]]},"DOI":"10.1016\/j.procs.2017.05.431","type":"journal-article","created":{"date-parts":[[2017,6,12]],"date-time":"2017-06-12T02:10:34Z","timestamp":1497233434000},"page":"1146-1151","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":51,"special_numbering":"C","title":["An Adaptive Implementation of \u03b5-Greedy in Reinforcement Learning"],"prefix":"10.1016","volume":"109","author":[{"given":"Alexandre","family":"dos Santos Mignon","sequence":"first","affiliation":[]},{"given":"Ricardo Luis","family":"de Azevedo da Rocha","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.procs.2017.05.431_bib0001","series-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"1998"},{"issue":"7","key":"10.1016\/j.procs.2017.05.431_bib0002","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1109\/T-LA.2007.4445748","article-title":"A Small Survey of the Evolution of Adaptivity and Adaptive Technology","volume":"5","author":"Neto","year":"2007","journal-title":"Revista IEEE Am\u00e9rica Latina"},{"key":"10.1016\/j.procs.2017.05.431_bib0003","first-page":"237","article-title":"Change Point Detection and Meta-Bandits for Online Learning in Dynamic Environments","author":"Hartland","year":"2007","journal-title":"CAp"},{"key":"10.1016\/j.procs.2017.05.431_bib0004","unstructured":"Luz, J.C.. Adaptive Technology Applied to Compiler Code Optimization. Master\u2019s thesis; Escola Polit\u00e9cnica, USP; 2004. (in Portuguese)."},{"key":"10.1016\/j.procs.2017.05.431_bib0005","unstructured":"Mignon, A.S., Rocha, R.L.A.. \u220a-Greedy Adaptativo. In: Mem\u00f3rias do VIII Workshop de Tecnologia Adaptativa - WTA 2014. S\u00e3o Paulo, Brazil; 2014, p. 57\u201362. (in Portuguese)."},{"issue":"1\/2","key":"10.1016\/j.procs.2017.05.431_bib0006","doi-asserted-by":"crossref","first-page":"100","DOI":"10.2307\/2333009","article-title":"Continuous Inspection Schemes","volume":"41","author":"Page","year":"1954","journal-title":"Biometrika"},{"key":"10.1016\/j.procs.2017.05.431_bib0007","series-title":"Proceedings of the 33rd Annual German Conference on Advances in Artificial Intelligence; KI\u201910","first-page":"203","article-title":"Adaptive \u220a-greedy Exploration in Reinforcement Learning Based on Value Differences","author":"Tokic","year":"2010"}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050917311134?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050917311134?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2018,8,31]],"date-time":"2018-08-31T19:27:19Z","timestamp":1535743639000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050917311134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":7,"alternative-id":["S1877050917311134"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2017.05.431","relation":{},"ISSN":["1877-0509"],"issn-type":[{"value":"1877-0509","type":"print"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An Adaptive Implementation of \u03b5-Greedy in Reinforcement Learning","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2017.05.431","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2017 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}