{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T10:50:37Z","timestamp":1730285437016,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"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":[[2022,4,25]]},"DOI":"10.1109\/noms54207.2022.9789809","type":"proceedings-article","created":{"date-parts":[[2022,6,9]],"date-time":"2022-06-09T21:21:22Z","timestamp":1654809682000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Factored Reinforcement Learning for Auto-scaling in Tandem Queues"],"prefix":"10.1109","author":[{"given":"Thomas","family":"Tournaire","sequence":"first","affiliation":[{"name":"Nokia Bell Labs France,SAMOVAR,Paris-Saclay,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Jin","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs France,Paris-Saclay,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Armen","family":"Aghasaryan","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs France,Paris-Saclay,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hind","family":"Castel-Taleb","sequence":"additional","affiliation":[{"name":"Telecom SudParis Evry,SAMOVAR,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanuel","family":"Hyon","sequence":"additional","affiliation":[{"name":"Université Paris Nanterre,UPL,Nanterre,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-91825-5_15"},{"key":"ref11","article-title":"Using Reinforcement Learning for Autonomic Resource allocation in clouds: Towards a fully automated workflow","author":"dutreilh","year":"2011","journal-title":"Icas"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIN.2018.8401621"},{"key":"ref13","article-title":"Hierarchical and factored reinforcement learning","author":"kozlova","year":"2010","journal-title":"Ph D Dissertation"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143877"},{"key":"ref15","first-page":"326","article-title":"Policy Iteration for factored MDPs","author":"koller","year":"2000"},{"key":"ref16","article-title":"Factored value iteration converges","author":"szita","year":"2008","journal-title":"CoRR"},{"key":"ref17","first-page":"740","article-title":"Efficient reinforcement learning in factored MDPs","volume":"2","author":"kearns","year":"1999","journal-title":"Proceedings of the 16th International Joint Conference on Artificial Intelligence"},{"key":"ref18","article-title":"Représentations graphiques de fonctions et processus décisionnels markoviens factorisés","author":"magnan","year":"2016","journal-title":"PhD thesis"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104288"},{"key":"ref3","article-title":"Optimal control policies for resource allocation in the cloud: comparison between markov decision process and heuristic approaches","author":"tournaire","year":"2021","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM46954.2019.9012702"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM46954.2019.9012674"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(00)00033-3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2924471"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/1094342017714530"},{"year":"2018","key":"ref1","article-title":"AWS Auto Scaling"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-011-0932-1"},{"key":"ref20","first-page":"213","article-title":"R-max - A general polynomial time algorithm for near-optimal Reinforcement Learning","volume":"3","author":"brafman","year":"2003","journal-title":"J Mach Learn Res"},{"article-title":"OpenAI GYM","year":"2016","author":"brockman","key":"ref21"}],"event":{"name":"NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium","start":{"date-parts":[[2022,4,25]]},"location":"Budapest, Hungary","end":{"date-parts":[[2022,4,29]]}},"container-title":["NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9789703\/9789704\/09789809.pdf?arnumber=9789809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T20:10:42Z","timestamp":1656965442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9789809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/noms54207.2022.9789809","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]}}}