References<\/strong><\/p>\n[1] Pearl, Judea. \u201cCausality\u201d. Cambridge University Press, 2009.<\/p>\n
[2] de Haan, Pim, Dinesh Jayaraman, and Sergey Levine. “Causal confusion in imitation learning.” In NeurIPS, 2019.<\/p>\n
[3] Irina Higgins et al., “Higgins, Irina, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. “beta-vae: Learning basic visual concepts with a constrained variational framework.” (2016).”, In ICLR, 2017.<\/p>\n
[4] Oord, Aaron van den, Oriol Vinyals, and Koray Kavukcuoglu. “Neural discrete representation learning.” In NeurIPS, 2017.<\/p>\n
[5] Dosovitskiy, Alexey, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. “CARLA: An open urban driving simulator.” In Conference on robot learning, 2017.<\/p>\n
[6] Srivastava, Nitish, Hinton, Geoffrey, Krizhevsky, Alex, Sutskever, Ilya, and Salakhutdinov, Ruslan. \u201cDropout: a simple way to prevent neural networks from overfitting\u201d. The Journal of Machine Learning Research, 15(1):1929\u20131958, 2014.<\/p>\n
[7] Ghiasi, Golnaz, Lin, Tsung-Yi, and Le, Quoc V. \u201cDropblock: A regularization method for convolutional networks\u201d. In NeurIPS, 2018.<\/p>\n
[8] DeVries, Terrance and Taylor, Graham W. \u201cImproved regularization of convolutional neural networks with cutout\u201d. arXiv preprint arXiv:1708.04552, 2017.<\/p>\n
[9] Yarats, Denis, Kostrikov, Ilya, and Fergus, Rob. \u201cImage augmentation is all you need: Regularizing deep reinforcement learning from pixels\u201d. In ICLR, 2021.<\/p>\n
[10] Shen, Zheyan, Cui, Peng, Kuang, Kun, Li, Bo, and Chen, Peixuan. \u201cCausally regularized learning with agnostic data selection bias\u201d. In ACM international conference on Multimedia, 2018.<\/p>\n
[11] Ho, Jonathan and Ermon, Stefano. \u201cGenerative adversarial imitation learning\u201d. In NeurIPS, 2016.<\/p>\n
[12] Brantley, Kiante, Sun, Wen, and Henaff, Mikael. \u201cDisagreement-regularized imitation learning\u201d. In ICLR, 2020.<\/p>\n","protected":false},"excerpt":{"rendered":"
Imitation learning has proven to be effective for learning sequential decision-making policies directly from expert demonstrations, reducing the need for costly and risky environmental interactions. Behavioral cloning is a simple form of imitation learning and learns a policy by solving a supervised learning problem over state-action pairs from expert demonstrations. Despite its simplicity, behavioral cloning […]<\/p>\n","protected":false},"author":34512,"featured_media":829420,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"msr-content-parent":199560,"footnotes":""},"research-area":[],"msr-locale":[268875],"class_list":["post-829402","msr-blog-post","type-msr-blog-post","status-publish","has-post-thumbnail","hentry","msr-locale-en_us"],"msr_assoc_parent":{"id":199560,"type":"lab"},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-blog-post\/829402"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-blog-post"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-blog-post"}],"author":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/users\/34512"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-blog-post\/829402\/revisions"}],"predecessor-version":[{"id":829417,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-blog-post\/829402\/revisions\/829417"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/829420"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=829402"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=829402"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=829402"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}