{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:37:36Z","timestamp":1730230656785,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096070","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Invariant Adversarial Imitation Learning From Visual Inputs"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Zhang","sequence":"first","affiliation":[{"name":"East China Normal University,School of Communications and Electronic Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghong","family":"Tian","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Communications and Electronic Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Lu","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Communications and Electronic Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Imitation learning as f-divergence minimization","year":"2019","author":"ke","key":"ref12"},{"key":"ref23","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","author":"yarats","year":"2021","journal-title":"Learning"},{"key":"ref15","article-title":"Learning belief representations for imitation learning in pomdps","author":"gangwani","year":"2019","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref14","first-page":"3016","article-title":"Visual adversarial imitation learning using variational models","volume":"34","author":"rafailov","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","author":"kostrikov","year":"2018","journal-title":"Learning"},{"key":"ref11","article-title":"A divergence minimization perspective on imitation learning methods","author":"seyed ghasemipour","year":"2019","journal-title":"Conference on Robot Learning"},{"article-title":"dm_control: Software and tasks for continuous control","year":"2020","author":"tassa","key":"ref22"},{"article-title":"Off-policy imitation learning from visual inputs","year":"2021","author":"cheng","key":"ref10"},{"article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","year":"2020","author":"kostrikov","key":"ref21"},{"key":"ref2","article-title":"Invariant causal representation learning for generalization in imitation and reinforcement learning","author":"lu","year":"2022","journal-title":"ICLR2022 Workshop on the Elements of Reasoning Objects Structure and Causality"},{"article-title":"The distracting control suite–a challenging benchmark for reinforcement learning from pixels","year":"2021","author":"stone","key":"ref1"},{"key":"ref17","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"Value-function approximations for partially observable markov decision processes","author":"milos","year":"2000","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref19","article-title":"Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref18","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"2019","journal-title":"Learning"},{"key":"ref8","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","author":"lee","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"ref7","article-title":"Reinforcement and imitation learning for diverse visuomotor skills","author":"kram\u00e1r","year":"2018","journal-title":"Robotics Science and Systems"},{"key":"ref9","article-title":"Causal confusion in imitation learning","author":"de haan","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref4","article-title":"Contrastive behavioral similarity embeddings for generalization in reinforcement learning","author":"agarwal","year":"2021","journal-title":"Learning"},{"key":"ref3","article-title":"Invariant causal imitation learning for generalizable policies","author":"bica","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref6","article-title":"Autonomous helicopter aerobatics through apprenticeship learning","author":"coates","year":"2010","journal-title":"The International Journal of Robotics Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390175"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096070.pdf?arnumber=10096070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:18Z","timestamp":1699902018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096070\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096070","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}