{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T23:14:25Z","timestamp":1780096465095,"version":"3.54.0"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"InnoHK CPII"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/lra.2021.3061397","type":"journal-article","created":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T20:48:36Z","timestamp":1614113316000},"page":"1880-1886","source":"Crossref","is-referenced-by-count":31,"title":["Adversarial Inverse Reinforcement Learning With Self-Attention Dynamics Model"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5633-1739","authenticated-orcid":false,"given":"Jiankai","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lantao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pinqian","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2858-1121","authenticated-orcid":false,"given":"Bo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4030-0684","authenticated-orcid":false,"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref11","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"3","author":"ziebart","year":"0","journal-title":"Proc 23rd Nat Conf Artif Intell"},{"key":"ref12","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","author":"fu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref13","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref14","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"chua","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"2450","article-title":"Recurrent world models facilitate policy evolution","author":"ha","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","first-page":"390","article-title":"End-to-end differentiable adversarial imitation learning","volume":"70","author":"baram","year":"0","journal-title":"Proc 34th Int Conf Mach Learn ser Proc Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref19","first-page":"1791","article-title":"Neural variational inference and learning in belief networks","volume":"32","author":"mnih","year":"0","journal-title":"Proc 31st Int Conf Mach Learn ser Proc Mach Learn Res"},{"key":"ref4","first-page":"2020","article-title":"Learning a decision module by imitating driver's control behaviors","author":"huang","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref27","first-page":"561","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","volume":"87","author":"mahmood","year":"0","journal-title":"Proc 2nd Conf Robot Learn ser Proc Mach Learn Res"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139555"},{"key":"ref6","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"0","journal-title":"Proc Seventeenth Int Conf Mach Learn ser ICML ’00"},{"key":"ref5","first-page":"2020","article-title":"Neuro-symbolic program search for autonomous driving decision module design","author":"sun","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref8","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390175"},{"key":"ref2","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref20","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"janner","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"chris","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","volume":"28","author":"heess","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn ser Proc Mach Learn Res"},{"key":"ref23","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197185"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9285111\/09361118.pdf?arnumber=9361118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:17Z","timestamp":1652194457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9361118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":27,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3061397","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}