{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T04:43:56Z","timestamp":1770353036938,"version":"3.49.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"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":[[2019,4]]},"DOI":"10.1109\/infcomw.2019.8845154","type":"proceedings-article","created":{"date-parts":[[2019,9,24]],"date-time":"2019-09-24T02:23:05Z","timestamp":1569291785000},"page":"435-442","source":"Crossref","is-referenced-by-count":29,"title":["Delay-Optimal Traffic Engineering through Multi-agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Pinyarash","family":"Pinyoanuntapong","sequence":"first","affiliation":[{"name":"University of North Carolina Charlotte, Charlotte, USA"}]},{"given":"Minwoo","family":"Lee","sequence":"additional","affiliation":[{"name":"University of North Carolina Charlotte, Charlotte, USA"}]},{"given":"Pu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of North Carolina Charlotte, Charlotte, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6567024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2010.5416357"},{"key":"ref3","volume-title":"The open mesh networks consortium"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2006.879350"},{"key":"ref5","article-title":"Utility-optimal wireless routing in the presence of heavy tails","author":"Lin","year":"2018","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref7","first-page":"5048","article-title":"Hindsight Experience Replay","volume-title":"Advances in Neural Information Processing Systems 30","author":"Andrychowicz","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.123"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225099"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219918"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SCC.2016.12"},{"key":"ref13","volume-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"Stampa","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2707140"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref16","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","volume-title":"Advances in neural information processing systems (NIPS)","author":"Boyan","year":"1994"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2002.1007796"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/EIConRusNW.2016.7448188"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/FRUCT.2017.8071304"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EIConRus.2017.7910517"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376469"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref23","first-page":"489","article-title":"Learning to cooperate via policy search","volume-title":"Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence","author":"Peshkin","year":"2000"},{"key":"ref24","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref25","first-page":"1928","article-title":"Asynchronous Methods for Deep Reinforcement Learning","volume-title":"International Conference on Machine Learning","author":"Mnih","year":"2016"},{"key":"ref26","volume-title":"Effective multi-step temporal-difference learning for non-linear function approximation","author":"van Seijen","year":"2016"},{"key":"ref27","volume-title":"Multi-step off-policy learning without importance sampling ratios","author":"Mahmood","year":"2017"},{"key":"ref28","article-title":"Per-decision multi-step temporal difference learning with control variates","volume-title":"Proceedings of the 2018 Conference on Uncertainty in Artificial Intelligence","author":"De Asis","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927542"},{"key":"ref30","first-page":"2613","article-title":"Double q-learning","volume-title":"Advances in Neural Information Processing Systems (NIPS)","volume":"23","author":"Hasselt","year":"2010"}],"event":{"name":"IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","location":"Paris, France","start":{"date-parts":[[2019,4,29]]},"end":{"date-parts":[[2019,5,2]]}},"container-title":["IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8831168\/8845034\/08845154.pdf?arnumber=8845154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T12:08:25Z","timestamp":1709294905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8845154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/infcomw.2019.8845154","relation":{},"subject":[],"published":{"date-parts":[[2019,4]]}}}