{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T03:20:25Z","timestamp":1730344825395,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.23919\/wiopt47501.2019.9144097","type":"proceedings-article","created":{"date-parts":[[2020,7,20]],"date-time":"2020-07-20T22:18:29Z","timestamp":1595283509000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["Beyond Max-weight Scheduling: A Reinforcement Learning-based Approach"],"prefix":"10.23919","author":[{"given":"Jeongmin","family":"Bae","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joohyun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Chong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/1300000001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/opre.9.3.383"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2012.2191157"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144097"},{"key":"ref14","first-page":"700","article-title":"Reinforcement learning algorithms for average-payoff markovian decision processes","volume":"94","author":"singh","year":"1994","journal-title":"AAAI"},{"key":"ref15","first-page":"2258","article-title":"Efficient average reward reinforcement learning using constant shifting values","author":"yang","year":"2016","journal-title":"AAAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0555"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704593"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1287\/moor.18.1.163"},{"key":"ref19","volume":"504","author":"sennott","year":"2009","journal-title":"Stochastic Dynamic Programming and the Control of Queueing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.1500356WC"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2007.897944"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2200\/S00271ED1V01Y201006CNT007"},{"key":"ref6","article-title":"Cellular-connected uavs over 5g: Deep reinforcement learning for interference management","author":"challita","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2850303"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997286"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/18.212277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2751641"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/9.182479"},{"key":"ref20","volume":"30","author":"hern\u00e1ndez-lerma","year":"2012","journal-title":"Discrete-Time Markov Control Processes Basic Optimality Criteria"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref23","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2016.2538238"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"}],"event":{"name":"2019 International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT)","start":{"date-parts":[[2019,6,3]]},"location":"Avignon, France","end":{"date-parts":[[2019,6,7]]}},"container-title":["2019 International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9137828\/9144084\/09144097.pdf?arnumber=9144097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T21:36:06Z","timestamp":1598304966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9144097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.23919\/wiopt47501.2019.9144097","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}