{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T17:36:44Z","timestamp":1762018604248,"version":"build-2065373602"},"reference-count":11,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":[[2019,8]]},"DOI":"10.1109\/mwscas.2019.8885080","type":"proceedings-article","created":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T23:44:38Z","timestamp":1572565478000},"page":"634-637","source":"Crossref","is-referenced-by-count":17,"title":["Q-learning based Routing Scheduling For a Multi-Task Autonomous Agent"],"prefix":"10.1109","author":[{"given":"Omar","family":"Bouhamed","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hakim","family":"Ghazzai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hichem","family":"Besbes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yehia","family":"Massoud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/opre.4.1.61"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2395536"},{"key":"ref10","article-title":"Safe and efficient off-policy reinforcement learning","author":"munos","year":"2016","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2885321"},{"journal-title":"Dynamic Programming","year":"2013","author":"bellman","key":"ref11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2666003"},{"key":"ref8","article-title":"Deep reinforcement learning for solving the vehicle routing problem","volume":"abs 1802 4240","author":"nazari","year":"2018","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TLA.2018.8444393"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2018.8623940"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2016.7847952"},{"journal-title":"Intelligent Autonomous Systems","year":"2015","author":"emanuele menegatti","key":"ref1"}],"event":{"name":"2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)","start":{"date-parts":[[2019,8,4]]},"location":"Dallas, TX, USA","end":{"date-parts":[[2019,8,7]]}},"container-title":["2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8882388\/8884793\/08885080.pdf?arnumber=8885080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:54:38Z","timestamp":1658094878000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8885080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/mwscas.2019.8885080","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}