{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:11:30Z","timestamp":1740100290802,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2062,61673237"],"award-info":[{"award-number":["U20B2062,61673237"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,19]]},"DOI":"10.1109\/itsc48978.2021.9564705","type":"proceedings-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T19:52:26Z","timestamp":1635191546000},"page":"726-733","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Task Long-Range Urban Driving Based on Hierarchical Planning and Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xiaoqin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mouyu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huimin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","first-page":"1087","article-title":"Mix & match agent curricula for reinforcement learning","volume":"80","author":"czarnecki","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref10","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","volume":"119","author":"badia","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref11","article-title":"Never give up: Learning directed exploration strategies","author":"badia","year":"2019","journal-title":"International Conference on Learning Representations"},{"journal-title":"Sparse curriculum reinforcement learning for end-to-end driving","year":"2021","author":"agarwal","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref14","article-title":"Distral: Robust multitask reinforcement learning","volume":"30","author":"teh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"166","article-title":"Modular multitask reinforcement learning with policy sketches","author":"andreas","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref17"},{"key":"ref18","first-page":"1","article-title":"Carla: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref28","article-title":"Variational autoencoder for deep learning of images, labels and captions","volume":"29","author":"pu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"journal-title":"End to End Learning for Self-Driving Cars","year":"2016","author":"bojarski","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref5","article-title":"Driving in dense traffic with model-free reinforcement learning","author":"saxena","year":"2019","journal-title":"Robotics"},{"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"},{"journal-title":"End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances (II)","year":"2019","author":"toromanoff","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1038\/s41586-020-03157-9","article-title":"First return, then explore","volume":"590","author":"ecoffet","year":"2021","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2018-9249"},{"key":"ref20","article-title":"Safe reinforcement learning for autonomous vehicles through parallel constrained policy optimization","author":"wen","year":"2020","journal-title":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)"},{"journal-title":"Social attention for autonomous decision-making in dense traffic","year":"2019","author":"leurent","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8216790"},{"key":"ref24","article-title":"Prm-rl: Long-range robotic navigation tasks by combining reinforcement learning and sampling-based planning","author":"faust","year":"2017","journal-title":"Artificial Intelligence"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0102-6"},{"key":"ref26","article-title":"Is deep reinforcement learning really superhuman on atari","author":"toromanoff","year":"2019","journal-title":"Deep Reinforcement Learning Workshop of 39th Conference on Neural Information Processing Systems (Neurips'2019)"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLR 2016 the 2016 International Conference on Learning Representations"}],"event":{"name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","start":{"date-parts":[[2021,9,19]]},"location":"Indianapolis, IN, USA","end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Intelligent Transportation Systems Conference (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9564393\/9564395\/09564705.pdf?arnumber=9564705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:40Z","timestamp":1652197660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/itsc48978.2021.9564705","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}