{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:26:48Z","timestamp":1761895608253,"version":"build-2065373602"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209801","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Safety-constrained Reinforcement Learning with Interaction-aware for Decision-making of Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Di","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Luo","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University,School of Computer and Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honglin","family":"Dong","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Lu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3054625"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134702"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref3"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"Haarnoja","key":"ref4"},{"article-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"Fujimoto","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"author":"Emmons","key":"ref8","article-title":"Rvs: What is essential for offline rl via supervised learning?"},{"article-title":"Autonomous ramp merge maneuver based on reinforcement learning with continuous action space","year":"2018","author":"Wang","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.10.024"},{"article-title":"End-to-end deep reinforcement learning for lane keeping assist","year":"2016","author":"Sallab","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/mci.2019.2901089"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DDCLS58216.2023.10166271"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534349"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341647"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01712"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3184990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3352811"},{"article-title":"Scene transformer: A unified architecture for predicting multiple agent trajectories","year":"2021","author":"Ngiam","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3372625"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422695"},{"article-title":"Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety","year":"2021","author":"Ma","key":"ref24"},{"article-title":"Saferl-kit: Evaluating efficient reinforcement learning methods for safe autonomous driving","year":"2022","author":"Zhang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17272"},{"key":"ref27","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Neural Information Processing Systems, Neural Information Processing Systems"},{"article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","year":"2014","author":"Chung","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"article-title":"Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving","year":"2020","author":"Zhou","key":"ref31"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209801.pdf?arnumber=11209801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:54:21Z","timestamp":1761890061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209801","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}