{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:52:50Z","timestamp":1781815970987,"version":"3.54.5"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"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":[[2018,11]]},"DOI":"10.1109\/icarcv.2018.8581213","type":"proceedings-article","created":{"date-parts":[[2019,1,9]],"date-time":"2019-01-09T13:57:00Z","timestamp":1547042220000},"page":"204-209","source":"Crossref","is-referenced-by-count":10,"title":["A Robotic Auto-Focus System based on Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xiaofan","family":"Yu","sequence":"first","affiliation":[{"name":"Center of Wireless Communication and Signal Processing, Peking University, Beijing, 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runze","family":"Yu","sequence":"additional","affiliation":[{"name":"Center of Wireless Communication and Signal Processing, Peking University, Beijing, 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingsong","family":"Yang","sequence":"additional","affiliation":[{"name":"Center of Wireless Communication and Signal Processing, Peking University, Beijing, 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Duan","sequence":"additional","affiliation":[{"name":"Center of Wireless Communication and Signal Processing, Peking University, Beijing, 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2003.1209511"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S1077-2014(03)00037-8"},{"key":"ref12","author":"metz","year":"2017","journal-title":"Discrete Sequential Prediction of Continuous Actions for Deep RL"},{"key":"ref13","first-page":"1334","article-title":"End-to-End Training of Deep Visuomotor Policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref14","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref15","first-page":"2829","article-title":"Continuous Deep Q-Learning with Model-based Acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref16","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2008.927976"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/6104.846935"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-015-9291-4"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.asoc.2009.07.007","article-title":"A Passive Auto-Focus Camera Control System","volume":"10","author":"chen","year":"2010","journal-title":"Applied Soft Computing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1117\/1.2130725"},{"key":"ref8","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":"ref7","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/cyto.a.22020"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/DISCOVER.2016.7806223"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the Game of Go without Human Knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref20","first-page":"317","article-title":"Neural Fitted Q Iteration-First Experiences with a Data Efficient Neural Reinforcement Learning Method","author":"riedmiller","year":"2005","journal-title":"European Conference on Machine Learning"},{"key":"ref21","first-page":"173","article-title":"Learning Hand-Eye Coordination for Robotic Grasping with Large-Scale Data Collection","author":"levine","year":"2016","journal-title":"International Symposium on Experimental Robotics"}],"event":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","location":"Singapore","start":{"date-parts":[[2018,11,18]]},"end":{"date-parts":[[2018,11,21]]}},"container-title":["2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8564369\/8580630\/08581213.pdf?arnumber=8581213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:08:08Z","timestamp":1781813288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8581213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icarcv.2018.8581213","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}