{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T13:40:15Z","timestamp":1761745215095},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":[[2020,3]]},"DOI":"10.1109\/6gsummit49458.2020.9083745","type":"proceedings-article","created":{"date-parts":[[2020,5,5]],"date-time":"2020-05-05T00:49:31Z","timestamp":1588639771000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Benchmarking Q-Learning Methods for Intelligent Network Orchestration in the Edge"],"prefix":"10.1109","author":[{"given":"Joel","family":"Reijonen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miljenko","family":"Opsenica","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tero","family":"Kauppinen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miika","family":"Komu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jimmy","family":"Kjallman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomas","family":"Mecklin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eero","family":"Hiltunen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jari","family":"Arkko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Timo","family":"Simanainen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Elmusrati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701336"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2705720"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2019.02.009"},{"journal-title":"Ericsson Research Blog","year":"2019","author":"arkko","key":"ref13"},{"journal-title":"Docker documentation","year":"2019","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800386"},{"journal-title":"Is Q-learning provably efficient","year":"2018","author":"jin","key":"ref16"},{"journal-title":"Keras The Python deep learning library","year":"2020","key":"ref17"},{"journal-title":"Dynamics of Boltzmann Q-learning in two-player two-action games","year":"2011","author":"kianercy","key":"ref4"},{"key":"ref3","first-page":"369","article-title":"Dynamic analysis of multiagent Q-learning with ?-greedy exploration","author":"gomes","year":"2009","journal-title":"Proceedings of the 26th International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WAINA.2017.67"},{"key":"ref8","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"2018","journal-title":"2nd Conference on Robot Learning (CoRL)"},{"key":"ref7","article-title":"Benchmarking Deep Reinforcement Learning for Continuous Control","author":"duan","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref2","first-page":"32","author":"sutton","year":"2014","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","first-page":"3","author":"alpaydin","year":"2010","journal-title":"Introduction to Machine Learning"},{"journal-title":"Benchmarking model-based reinforcement learning","year":"2019","author":"wang","key":"ref9"}],"event":{"name":"2020 2nd 6G Wireless Summit (6G SUMMIT)","start":{"date-parts":[[2020,3,17]]},"location":"Levi, Finland","end":{"date-parts":[[2020,3,20]]}},"container-title":["2020 2nd 6G Wireless Summit (6G SUMMIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9075870\/9083733\/09083745.pdf?arnumber=9083745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:56:26Z","timestamp":1656345386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9083745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/6gsummit49458.2020.9083745","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}