{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:23:30Z","timestamp":1730204610642,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/V043676\/1"],"award-info":[{"award-number":["EP\/V043676\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"ERC","doi-asserted-by":"publisher","award":["101089047"],"award-info":[{"award-number":["101089047"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10384207","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:36Z","timestamp":1705671516000},"page":"5631-5638","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning for Stochastic Max-Plus Linear Systems"],"prefix":"10.1109","author":[{"given":"Vignesh","family":"Subramanian","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farzaneh","family":"Farhadi","sequence":"additional","affiliation":[{"name":"School of Engineering, Newcastle University,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sadegh","family":"Soudjani","sequence":"additional","affiliation":[{"name":"School of Computing, Newcastle University,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-68612-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1515\/9781400865239"},{"volume-title":"Max-plus linear stochastic systems and perturbation analysis","year":"2007","author":"Heidergott","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref5","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2006.02.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/0325013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF01797154"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2793662"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139194655"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3195152"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/9.486651"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)31515-X"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3182\/20140514-3-FR-4046.00025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WODES.2016.7497879"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10696-0_7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2502781"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.01.002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.04.060"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57628-8_10"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107714"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ-IEEE.2019.8859012"},{"issue":"3","key":"ref23","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-Iearning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine learning"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"arXiv preprint"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10384207.pdf?arnumber=10384207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:47:44Z","timestamp":1706010464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10384207\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10384207","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}