{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:29:44Z","timestamp":1763202584304,"version":"3.28.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636449","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"130-136","source":"Crossref","is-referenced-by-count":5,"title":["Latent Attention Augmentation for Robust Autonomous Driving Policies"],"prefix":"10.1109","author":[{"given":"Ran","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Christopher","family":"Agia","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Shkurti","sequence":"additional","affiliation":[]},{"given":"David","family":"Meger","sequence":"additional","affiliation":[]},{"given":"Gregory","family":"Dudek","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"An empirical evaluation of deep learning on highway driving","author":"huval","year":"2015","journal-title":"arXiv preprint arXiv 1504 01716"},{"key":"ref38","article-title":"Safe, multiagent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016","journal-title":"arXiv preprint arXiv 1610 03677"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197408"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref37","article-title":"Torcs, the open racing car simulator","volume":"4","author":"wymann","year":"2000"},{"key":"ref36","article-title":"Deep reinforcement learning for autonomous driving","author":"wang","year":"2018","journal-title":"arXiv preprint arXiv 1811 11329"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FBIT.2007.37"},{"key":"ref10","first-page":"1696","article-title":"Task-agnostic dynamics priors for deep reinforcement learning","author":"du","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.048"},{"key":"ref11","first-page":"1","article-title":"Data efficient reinforcement learning for legged robots","author":"yang","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref12","first-page":"839","article-title":"Multi-objective model-based policy search for data-efficient learning with sparse rewards","author":"kaushik","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1985.6313353"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IFIC.2000.862462"},{"key":"ref15","article-title":"Airsim: High-fidelity visual and physical simulation for autonomous vehicles","author":"shah","year":"2017","journal-title":"Field and Service Robotics"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref17","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref19","article-title":"Cad2rl: Real single-image flight without a single real image","author":"sadeghi","year":"2016","journal-title":"arXiv preprint arXiv 1611 04201"},{"key":"ref28","article-title":"Deep attention recurrent q-network","author":"sorokin","year":"2015","journal-title":"arXiv preprint arXiv 1512 01882"},{"key":"ref4","first-page":"7613","article-title":"Maven: Multi-agent variational exploration","author":"mahajan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"935","article-title":"Plan2vec: Unsupervised representation learning by latent plans","author":"yang","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref3","article-title":"Driving policy transfer via modularity and abstraction","author":"m\u00fcller","year":"2018","journal-title":"arXiv preprint arXiv 1804 09023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref29","article-title":"Unlocking pixels for reinforcement learning via implicit attention","author":"choromanski","year":"2021","journal-title":"arXiv preprint arXiv 2102 05988"},{"key":"ref5","article-title":"Roma: Multi-agent reinforcement learning with emergent roles","author":"wang","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"article-title":"Residual reinforcement learning for robot control","year":"2018","author":"johannink","key":"ref8"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref2","article-title":"Robust policies via mid-level visual representations: An experimental study in manipulation and navigation","author":"chen","year":"2020","journal-title":"arXiv preprint arXiv 2011 00177"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793735"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw6661"},{"key":"ref46","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref20","article-title":"Navigation in the service of enhanced pose estimation","author":"manderson","year":"2018","journal-title":"International Symposium on Experimental Robotics (ISER)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00751"},{"key":"ref22","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref47","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.223"},{"key":"ref42","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref24","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","author":"lee","year":"2019","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0042-6989(89)90006-0"},{"key":"ref23","first-page":"2170","article-title":"Deepmdp: Learning continuous latent space models for representation learning","author":"gelada","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref26","article-title":"Learning invariant representations for reinforcement learning without reconstruction","author":"zhang","year":"2020","journal-title":"arXiv preprint arXiv 2006 10226"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/130912839"},{"key":"ref25","article-title":"Improving sample efficiency in model-free reinforcement learning from images","author":"yarats","year":"2019","journal-title":"arXiv preprint arXiv 1910 01741"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2021,9,27]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636449.pdf?arnumber=9636449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T22:40:12Z","timestamp":1674081612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636449","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}