{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T02:19:52Z","timestamp":1783477192772,"version":"3.55.0"},"reference-count":23,"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\/isqed48828.2020.9136980","type":"proceedings-article","created":{"date-parts":[[2020,7,9]],"date-time":"2020-07-09T20:46:45Z","timestamp":1594327605000},"page":"323-328","source":"Crossref","is-referenced-by-count":14,"title":["An Efficient Deep Reinforcement Learning Framework for UAVs"],"prefix":"10.1109","author":[{"given":"Shanglin","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingbing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caiwu","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caiwen","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"43","article-title":"Actor-critic reinforcement learning with energy-based policies","author":"nicolas","year":"2012","journal-title":"EWRL"},{"key":"ref11","first-page":"1097","article-title":"Image agenet classification with deep convolutional neural networks","author":"alex","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref14","article-title":"Playing atari with deep reinforcement learning","volume":"abs 1312 5602","author":"volodymyr","year":"2013","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"volodymyr","year":"2015","journal-title":"Nature"},{"key":"ref16","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"0","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref17","author":"schaul","year":"2015","journal-title":"Prioritized experience replay"},{"key":"ref18","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref19","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"volodymyr","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref4","first-page":"1","article-title":"Convergence of q-learning: A simple proof","author":"francisco","year":"2001","journal-title":"Institute of Systems and Robotics Tech Rep"},{"key":"ref3","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","article-title":"Learning from delayed rewards (phd dissertation)","author":"watkins","year":"1989","journal-title":"King's College Cambridge UK"},{"key":"ref5","article-title":"Deep reinforcement learning","author":"david","year":"2016","journal-title":"Tutorial at ICML"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/203330.203343","article-title":"Temporal difference learning and td-gammon","volume":"38","author":"gerald","year":"1995","journal-title":"Communications of the ACM"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"christopher","year":"1992","journal-title":"Machine Learning"},{"key":"ref2","article-title":"Latest version of gazebo simulator makes it easier than ever to not build a robot","author":"evan","year":"2016"},{"key":"ref1","year":"0","journal-title":"Gazebo Robot Simulation"},{"key":"ref9","first-page":"1063","article-title":"Reinforcement learning with factored states and actions","volume":"5","author":"brian","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","year":"2017","journal-title":"Deep reinforcement learning scripts working with ros+gazebo+” gym like wrappers"},{"key":"ref22","year":"0","journal-title":"Px4 autopilot user guide (master)"},{"key":"ref21","author":"kojcev","year":"2018","journal-title":"Evaluation of deep reinforcement learning methods for modular robots"},{"key":"ref23","year":"0","journal-title":"Robot operating system (ros) introduction documentation"}],"event":{"name":"2020 21st International Symposium on Quality Electronic Design (ISQED)","location":"Santa Clara, CA, USA","start":{"date-parts":[[2020,3,25]]},"end":{"date-parts":[[2020,3,26]]}},"container-title":["2020 21st International Symposium on Quality Electronic Design (ISQED)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9131689\/9136966\/09136980.pdf?arnumber=9136980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:52:38Z","timestamp":1656453158000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9136980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/isqed48828.2020.9136980","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}