{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:28:55Z","timestamp":1773156535361,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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.2019.8845212","type":"proceedings-article","created":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T22:23:05Z","timestamp":1569277385000},"page":"496-501","source":"Crossref","is-referenced-by-count":9,"title":["Exploring Deep Reinforcement Learning for Autonomous Powerline Tracking"],"prefix":"10.1109","author":[{"given":"Panin","family":"Pienroj","sequence":"first","affiliation":[]},{"given":"Sandro","family":"Schonborn","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Birke","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","volume":"48","author":"gu","year":"0","journal-title":"Proceedings of ICML"},{"key":"ref11","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proceedings of NIPS"},{"key":"ref12","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","volume":"70","author":"chou","year":"0","journal-title":"Proceedings of ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref14","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"0","journal-title":"Proceedings of ICML"},{"key":"ref15","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"0","journal-title":"Proceedings of ICML"},{"key":"ref17","article-title":"Airsim: High-fidelity visual and physical simulation for autonomous vehicles","author":"shah","year":"2017","journal-title":"Field and Service Robotics"},{"key":"ref18","year":"0","journal-title":"Unreal engine 4"},{"key":"ref19","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICSGCE.2016.7876026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532456"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/772"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MELCON.2014.6820566"},{"key":"ref5","author":"vinyals","year":"2019","journal-title":"Alphastar Mastering the real-time strategy game StarCraft II"},{"key":"ref8","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"0","journal-title":"Proceedings of AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2014.6842267"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"wang","year":"0","journal-title":"Proceedings of ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref20","article-title":"The OpenCV Library","author":"bradski","year":"2000","journal-title":"Dr Dobb's Journal of Software Tools"},{"key":"ref22","first-page":"39:1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206247"},{"key":"ref26","author":"fran\u00e7ois-lavet","year":"2017","journal-title":"Contributions to deep reinforcement learning and its applications in smartgrids"},{"key":"ref25","article-title":"Virtual to real reinforcement learning for autonomous driving","author":"pan","year":"2017","journal-title":"BMVC"}],"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\/08845212.pdf?arnumber=8845212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:19:53Z","timestamp":1658143193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8845212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/infcomw.2019.8845212","relation":{},"subject":[],"published":{"date-parts":[[2019,4]]}}}