{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T12:22:13Z","timestamp":1778070133236,"version":"3.51.4"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"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":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tits.2022.3227738","type":"journal-article","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T18:44:11Z","timestamp":1671216251000},"page":"2874-2887","source":"Crossref","is-referenced-by-count":114,"title":["Modeling Human Driving Behavior Through Generative Adversarial Imitation Learning"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9254-8417","authenticated-orcid":false,"given":"Raunak","family":"Bhattacharyya","sequence":"first","affiliation":[{"name":"Oxford Robotics Institute, University of Oxford, Oxford, U.K"}]},{"given":"Blake","family":"Wulfe","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA, USA"}]},{"given":"Derek J.","family":"Phillips","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA, USA"}]},{"given":"Alex","family":"Kuefler","sequence":"additional","affiliation":[{"name":"Department of Symbolic Systems, Stanford University, Stanford, CA, USA"}]},{"given":"Jeremy","family":"Morton","sequence":"additional","affiliation":[{"name":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA"}]},{"given":"Ransalu","family":"Senanayake","sequence":"additional","affiliation":[{"name":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7238-9663","authenticated-orcid":false,"given":"Mykel J.","family":"Kochenderfer","sequence":"additional","affiliation":[{"name":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"U.S. highway 101 dataset","author":"Colyar","year":"2007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317913"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2018.2804159"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317943"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917297"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2016.7535559"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2013.6728466"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2012.6232277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01026"},{"key":"ref12","first-page":"1","article-title":"Multiple futures prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Tang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917132"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995790"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916982"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794007"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0191-2615(81)90037-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995721"},{"key":"ref21","first-page":"1","article-title":"Continuous inverse optimal control with locally optimal examples","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Levine"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2603007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref26","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Ross"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(00)00115-4"},{"key":"ref28","first-page":"1","article-title":"A game-theoretic approach to apprenticeship learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Syed"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040156"},{"key":"ref30","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI Conf. Artif. Intell. (AAAI)","author":"Ziebart"},{"key":"ref31","first-page":"1","article-title":"Modeling interaction via the principle of maximum causal entropy","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ziebart"},{"key":"ref32","first-page":"1","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Ho"},{"key":"ref33","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Goodfellow"},{"key":"ref34","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Schulman"},{"key":"ref35","first-page":"1","article-title":"InfoGAIL: Interpretable imitation learning from visual demonstrations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"key":"ref36","first-page":"1","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref37","first-page":"1","article-title":"Burn-in demonstrations for multi-modal imitation learning","volume-title":"Proc. Int. Conf. Auto. Agents MultiAgent Syst. (AAMAS)","author":"Kuefler"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593758"},{"key":"ref39","first-page":"1","article-title":"Multi-agent generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Song"},{"key":"ref40","first-page":"7194","article-title":"Multi-agent adversarial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yu"},{"key":"ref41","first-page":"1855","article-title":"Multi-agent adversarial inverse reinforcement learning with latent variables","volume-title":"Proc. Int. Conf. Auto. Agents Multi-Agent Syst. (AAMAS)","author":"Gruver"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref43","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Foerster"},{"key":"ref44","first-page":"1","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sukhbaatar"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.0-184"},{"key":"ref46","first-page":"443","article-title":"Lenient multi-agent deep reinforcement learning","volume-title":"Proc. Int. Conf. Auto. Agents MultiAgent Syst. (AAMAS)","author":"Palmer"},{"key":"ref47","article-title":"Parameter sharing for heterogeneous agents in multi-agent reinforcement learning","author":"Terry","year":"2020","journal-title":"arXiv:2005.13625"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"ref52","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2003.1251975"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2006.884616"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2192262"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6858871"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957766"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2007.4290245"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/jigpal\/jzp049"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344136"},{"key":"ref62","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Duan"},{"key":"ref63","first-page":"1","article-title":"Improved training of Wasserstein GANs","author":"Gulrajani","year":"2017","journal-title":"Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793750"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317738"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref67","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018","journal-title":"arXiv:1806.01261"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87479-9_61"},{"key":"ref69","first-page":"1","article-title":"Deep implicit coordination graphs for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Auto. Agents MultiAgent Syst. (AAMAS)","author":"Li"},{"key":"ref70","first-page":"1","article-title":"SQIL: Imitation learning via regularized behavioral cloning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Reddy"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10057093\/09990591.pdf?arnumber=9990591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T10:53:59Z","timestamp":1706784839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9990591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":70,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tits.2022.3227738","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}