{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:07:33Z","timestamp":1759010853568,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812400","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"7263-7269","source":"Crossref","is-referenced-by-count":2,"title":["HR-Planner: A Hierarchical Highway Tactical Planner based on Residual Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Wu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyang","family":"Zhuang","sequence":"additional","affiliation":[{"name":"University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/682"},{"key":"ref31","first-page":"2012","article-title":"Dac: The double actor-critic architecture for learning options","volume":"32","author":"zhang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509799"},{"key":"ref34","first-page":"1","article-title":"Carla: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Conference on Robot Learning"},{"journal-title":"An end-to-end deep reinforcement learning approach for the long-term short-term planning on the frenet space","year":"2020","author":"moghadam","key":"ref10"},{"journal-title":"Trajectory planning for autonomous vehicles using hierarchical reinforcement learning","year":"2020","author":"naveed","key":"ref11"},{"journal-title":"A safe hierarchical planning framework for complex driving scenarios based on reinforcement learning","year":"2021","author":"li","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.039"},{"journal-title":"Residual Policy Learning","year":"2018","author":"silver","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning.","author":"lillicrap","year":"2016","journal-title":"ICLR (Poster)"},{"key":"ref18","article-title":"Parameter space noise for exploration","author":"plappert","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref19","article-title":"Noisy networks for exploration","author":"fortunato","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref28","first-page":"2469","article-title":"Policy optimization with demonstrations","author":"kang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2106158"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5953"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917304"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341496"},{"key":"ref7","first-page":"0","article-title":"Attention-based hierarchical deep reinforcement learning for lane change behaviors in autonomous driving","author":"chen","year":"2019","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341647"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3115980"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10744"},{"journal-title":"Progressive neural networks","year":"2016","author":"rusu","key":"ref21"},{"journal-title":"Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations","year":"2018","author":"zhang","key":"ref24"},{"journal-title":"Transfer Learning in Deep Reinforcement Learning A Survey","year":"2020","author":"zhu","key":"ref23"},{"key":"ref26","first-page":"1040","article-title":"Learning from demonstration","author":"schaal","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2022,5,23]]},"location":"Philadelphia, PA, USA","end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812400.pdf?arnumber=9812400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:07:44Z","timestamp":1667516864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812400","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}