{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T10:24:06Z","timestamp":1756895046770,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.23919\/acc45564.2020.9147960","type":"proceedings-article","created":{"date-parts":[[2020,7,27]],"date-time":"2020-07-27T22:02:33Z","timestamp":1595887353000},"page":"3242-3248","source":"Crossref","is-referenced-by-count":3,"title":["Smooth Actor-Critic Algorithm for End-to-End Autonomous Driving"],"prefix":"10.23919","author":[{"given":"Wenjie","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shixian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changle","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep reinforcement learning for autonomous driving","author":"wang","year":"2018","journal-title":"arXiv preprint arXiv 1811 11329"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"article-title":"Reinforcement learning an introduction–second edition, in progress (draft)","year":"2015","author":"sutton","key":"ref12"},{"key":"ref13","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63004-5_6"},{"key":"ref18","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML-15)"},{"key":"ref19","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0"},{"key":"ref4","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/robotics2030122"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref8","article-title":"Torcs, the open racing car simulator","volume":"4","author":"wymann","year":"2000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"ref2","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05952"},{"key":"ref9","article-title":"Beyond grand theft auto v for training, testing and enhancing deep learning in self driving cars","author":"martinez","year":"2017","journal-title":"arXiv preprint arXiv 1712 01397"},{"key":"ref1","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":"ref20","first-page":"5285","article-title":"Scalable trust-region method for deep reinforcement learning using kroneckerfactored approximation","author":"wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref24","first-page":"2891","article-title":"Query-efficient imitation learning for end-to-end simulated driving","author":"zhang","year":"2017","journal-title":"31st AAAI Conference on Artificial Intelligence AAAI 2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref25","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"}],"event":{"name":"2020 American Control Conference (ACC)","start":{"date-parts":[[2020,7,1]]},"location":"Denver, CO, USA","end":{"date-parts":[[2020,7,3]]}},"container-title":["2020 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9140048\/9147203\/09147960.pdf?arnumber=9147960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,31]],"date-time":"2020-08-31T21:47:27Z","timestamp":1598910447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9147960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.23919\/acc45564.2020.9147960","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}