{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:23:23Z","timestamp":1778801003450,"version":"3.51.4"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276126"],"award-info":[{"award-number":["62276126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62250069"],"award-info":[{"award-number":["62250069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20324"],"award-info":[{"award-number":["U24A20324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Jiangsu","award":["BK2024119"],"award-info":[{"award-number":["BK2024119"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2025.3552228","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:35:11Z","timestamp":1742232911000},"page":"5600-5612","source":"Crossref","is-referenced-by-count":2,"title":["Generalizable Multi-Modal Adversarial Imitation Learning for Non-Stationary Dynamics"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9908-5303","authenticated-orcid":false,"given":"Yi-Chen","family":"Li","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3070-8275","authenticated-orcid":false,"given":"Ningjing","family":"Chao","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9238-4747","authenticated-orcid":false,"given":"Zongzhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7251-4372","authenticated-orcid":false,"given":"Fuxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7803-0766","authenticated-orcid":false,"given":"Lei","family":"Yuan","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-5447","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. 29th Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref3","article-title":"Understanding adversarial imitation learning in small sample regime: A stage-coupled analysis","author":"Xu","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560942"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref8","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu"},{"key":"ref9","article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kostrikov"},{"key":"ref10","first-page":"5587","article-title":"Policy improvement via imitation of multiple oracles","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref11","first-page":"3812","article-title":"InfoGAIL: Interpretable imitation learning from visual demonstrations","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref12","first-page":"2181","article-title":"Learning and retrieval from prior data for skill-based imitation learning","volume-title":"Proc. Ann. Conf. Robot. Learn.","author":"Nasiriany"},{"key":"ref13","article-title":"Imitation learning from observations under transition model disparity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gangwani"},{"key":"ref14","first-page":"8510","article-title":"Offline imitation learning with a misspecified simulator","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref16","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagabandi"},{"key":"ref17","first-page":"1235","article-title":"Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Hausman"},{"key":"ref18","article-title":"Generative adversarial imitation from observation","author":"Torabi","year":"2018"},{"key":"ref19","article-title":"State-only imitation with transition dynamics mismatch","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gangwani"},{"key":"ref20","first-page":"1071","article-title":"Out-of-dynamics imitation learning from multimodal demonstrations","volume-title":"Proc. Ann. Conf. Robot. Learn.","author":"Qiu"},{"key":"ref21","first-page":"2828","article-title":"Robust imitation learning against variations in environment dynamics","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Chae"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref23","first-page":"7799","article-title":"On the expressivity of Markov reward","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Abel"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2003.813506"},{"key":"ref27","article-title":"Notes on Kullback-Leibler divergence and likelihood","author":"Shlens","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3099621"},{"key":"ref29","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"Christiano","year":"2016"},{"key":"ref30","article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach"},{"key":"ref31","first-page":"18050","article-title":"Effective diversity in population based reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Parker-Holder"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20730"},{"key":"ref33","first-page":"2465","article-title":"Fast teammate adaptation in the presence of sudden policy change","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Zhang"},{"key":"ref34","article-title":"Quantifying zero-shot coordination capability with behavior preferring partners","author":"Wang","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1561\/2200000044"},{"key":"ref36","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref37","first-page":"5320","article-title":"Robust imitation of diverse behaviors","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/405"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref40","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"},{"key":"ref41","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Sodhani"},{"key":"ref42","volume-title":"Foundations of Machine Learning","author":"Mohri","year":"2012"},{"key":"ref43","first-page":"5767","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Gulrajani"},{"key":"ref44","first-page":"2434","article-title":"Towards more generalizable one-shot visual imitation learning","volume-title":"Proc. IEEE Int. Conf. Robot. Autom.","author":"Zhao"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97304-3_25"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref49","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref50","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref51","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","volume-title":"Proc. Ann. Conf. Robot. Learn.","author":"Finn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977835"},{"key":"ref53","first-page":"783","article-title":"Task-embedded control networks for few-shot imitation learning","volume-title":"Proc. Ann. Conf. Robot. Learn.","author":"James"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwac123"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05939-8"},{"key":"ref56","first-page":"32926","article-title":"State regularized policy optimization on data with dynamics shift","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Xue"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3459991"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10930709.pdf?arnumber=10930709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:42:01Z","timestamp":1749231721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10930709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":57,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3552228","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}