{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T19:14:34Z","timestamp":1778094874818,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9560907","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"1036-1042","source":"Crossref","is-referenced-by-count":41,"title":["Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Pin","family":"Wang","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dapeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Zenseact, Chalmers University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanhan","family":"Li","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Yao","family":"Chan","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139555"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813903"},{"key":"ref13","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016","journal-title":"arXiv preprint arXiv 1610 03677"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917221"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995721"},{"key":"ref17","first-page":"5767","article-title":"Improved training of wasserstein gans","author":"gulrajani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Wasserstein adversarial imitation learning","author":"xiao","year":"2019","journal-title":"arXiv preprint arXiv 1906 02916"},{"key":"ref19","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"ref4","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"ref6","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"ziebart","year":"2010","journal-title":"Ph D Dissertation"},{"key":"ref5","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref8","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"fu","year":"2017","journal-title":"arXiv preprint arXiv 1710 11248"},{"key":"ref7","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref9","article-title":"A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models","author":"finn","year":"2016","journal-title":"arXiv preprint arXiv 1611 03852"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.64"},{"key":"ref22","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref21","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1201\/9781498701822"},{"key":"ref23","volume":"2","author":"\u00e5str\u00f6m","year":"1995","journal-title":"PID Controllers Theory Design and Tuning"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09560907.pdf?arnumber=9560907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:22:57Z","timestamp":1659482577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560907","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}