{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T01:02:01Z","timestamp":1794013321062,"version":"4.8.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610878","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"14428-14434","source":"Crossref","is-referenced-by-count":17,"title":["Reinforcement Learning with Human Feedback for Realistic Traffic Simulation"],"prefix":"10.1109","author":[{"given":"Yulong","family":"Cao","sequence":"first","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boris","family":"Ivanovic","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaowei","family":"Xiao","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Pavone","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Driving to Safety: How Many Miles of Driving Would It Take to Demonstrate Autonomous Vehicle Reliability?","author":"Kalra","year":"2016"},{"key":"ref2","article-title":"Waymo safety report","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161463"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3141\/1852-16"},{"key":"ref8","first-page":"86","article-title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","volume-title":"Conference on Robot Learning (CoRL)","author":"Chai"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01659"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00978"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793740"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3091477"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01679"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160296"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23780-5_11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_8"},{"key":"ref19","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume":"26","author":"Griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","author":"Jaques","year":"2019","journal-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.05.014"},{"key":"ref23","author":"Ziegler","year":"2019","journal-title":"Fine-tuning language models from human preferences"},{"key":"ref24","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","author":"Abramson","year":"2022","journal-title":"Improving multimodal interactive agents with reinforcement learning from human feedback"},{"key":"ref27","article-title":"Chatgpt for robotics: Design principles and model abilities","volume-title":"Microsoft, Tech. Rep. MSR-TR-2023-8","author":"Vemprala","year":"2023"},{"key":"ref28","article-title":"Scaling laws for reward model overoptimization","author":"Gao","year":"2022"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610878.pdf?arnumber=10610878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:58:28Z","timestamp":1723269508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610878","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}