{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:10:30Z","timestamp":1771956630417,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8793750","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"789-795","source":"Crossref","is-referenced-by-count":33,"title":["Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning"],"prefix":"10.1109","author":[{"given":"Raunak P.","family":"Bhattacharyya","sequence":"first","affiliation":[]},{"given":"Derek J.","family":"Phillips","sequence":"additional","affiliation":[]},{"given":"Changliu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jayesh K.","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Katherine","family":"Driggs-Campbell","sequence":"additional","affiliation":[]},{"given":"Mykel J.","family":"Kochenderfer","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593758"},{"key":"ref11","article-title":"Multi-agent generative adversarial imitation learning","author":"song","year":"2018","journal-title":"International Conference on Learning Representations (ICLR) Workshop Track"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref13","first-page":"3815","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","author":"li","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref14","first-page":"1890","article-title":"Imitation learning with demonstrations and shaping rewards","author":"judah","year":"2014","journal-title":"AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"ref15","article-title":"Imitation learning with a value-based prior","author":"syed","year":"2012","journal-title":"arXiv preprint arXiv 1206 5290"},{"key":"ref16","first-page":"475","article-title":"Reinforcement learning from simultaneous human and MDP reward","author":"knox","year":"2012","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4271\/2016-01-0128"},{"key":"ref3","year":"2011","journal-title":"ISO\/WD 26262-1 Road vehicles - Functional Safety"},{"key":"ref6","author":"colyar","year":"2007","journal-title":"US Highway 101 Dataset"},{"key":"ref5","first-page":"317","article-title":"Closed-loop policies for operational tests of safety-critical systems","author":"morton","year":"2018","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995721"},{"key":"ref7","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref20","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref22","article-title":"Rail: Risk-averse imitation learning","author":"santara","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref21","first-page":"214","article-title":"Wasserstein Generative Adversarial Networks","author":"arjovsky","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref24","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"201","journal-title":"International Conference on Machine Learning (ICML)"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08793750.pdf?arnumber=8793750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:17:50Z","timestamp":1657855070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793750","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}