{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T04:19:43Z","timestamp":1742617183209,"version":"3.40.2"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022YFB2601802"],"award-info":[{"award-number":["2022YFB2601802"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,24]]},"DOI":"10.1109\/itsc58415.2024.10920026","type":"proceedings-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T19:00:11Z","timestamp":1742583611000},"page":"856-863","source":"Crossref","is-referenced-by-count":0,"title":["Refine Reinforcement Learning for Safety Training of Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Fukun","family":"Yang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China"}]},{"given":"Zhiqun","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China"}]},{"given":"Yuanming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications,Chongqing,China"}]},{"given":"Guixin","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06111-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref5","author":"Tessler","year":"2018","journal-title":"Reward constrained policy optimization"},{"key":"ref6","article-title":"Constrained reinforcement learning has zero duality gap","volume":"32","author":"Paternain","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"International Conference on Machine Learning","author":"Stooke"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294259"},{"key":"ref11","author":"Leurent","year":"2018","journal-title":"An environment for autonomous driving decision-making"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref14","volume-title":"An investigation and design of slip control braking systems integrated with four-wheel steering","author":"Taheri","year":"1990"},{"key":"ref15","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"Graph attention networks"},{"key":"ref16","author":"Cordonnier","year":"2020","journal-title":"Multi-head attention: Collaborate instead of concatenate"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"}],"event":{"name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","location":"Edmonton, AB, Canada","start":{"date-parts":[[2024,9,24]]},"end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10919469\/10919190\/10920026.pdf?arnumber=10920026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T23:20:44Z","timestamp":1742599244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10920026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/itsc58415.2024.10920026","relation":{},"subject":[],"published":{"date-parts":[[2024,9,24]]}}}