{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:32:36Z","timestamp":1730255556731,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811663","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"3591-3597","source":"Crossref","is-referenced-by-count":1,"title":["Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Elie","family":"Aljalbout","sequence":"first","affiliation":[{"name":"Technical University of Munich (TUM),Munich,Germany,80797"}]},{"given":"Maximilian","family":"Ulmer","sequence":"additional","affiliation":[{"name":"Technical University of Munich (TUM),Munich,Germany,80797"}]},{"given":"Rudolph","family":"Triebel","sequence":"additional","affiliation":[{"name":"Technical University of Munich (TUM),Munich,Germany,80797"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref33","article-title":"State entropy maximization with random encoders for efficient exploration","author":"seo","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref30","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Deepmind control suite","author":"tassa","year":"2018","journal-title":"ArXiv Preprint"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"ref34","article-title":"De-coupling representation learning from reinforcement learning","author":"stooke","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"From variational to deterministic autoencoders","author":"ghosh","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref40","first-page":"3733","article-title":"Unsuper-vised feature learning via non-parametric instance discrimination","author":"wu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","first-page":"2672","article-title":"Generative adversarial nets","volume":"2","author":"goodfellow","year":"0","journal-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems"},{"key":"ref12","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref13","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref14","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"henaff","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"key":"ref15","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref16","first-page":"1480","article-title":"Darla: Improving zero-shot transfer in reinforcement learning","author":"higgins","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"2721","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref4","first-page":"279","article-title":"Modular learning in neural networks","author":"ballard","year":"1987","journal-title":"AAAI"},{"key":"ref27","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Making curiosity explicit in vision-based rl","author":"aljalbout","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Learning and generalisation of primitives skills towards robust dual-arm manipulation","author":"pairet","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"Distributional policy gradients","author":"barth-maron","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref8","article-title":"Robust policies via mid-level visual representations: An experimental study in manipulation and navigation","author":"chen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Exploration by random network distillation","author":"burda","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref2","article-title":"Learning vision-based reactive policies for obstacle avoidance","author":"aljalbout","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197181"},{"key":"ref20","article-title":"Auto-Encoding Variational Bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref22","first-page":"5639","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"laskin","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref41","article-title":"Improving sample efficiency in model-free reinforcement learning from images","author":"yarats","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref26","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2022,5,23]]},"location":"Philadelphia, PA, USA","end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811663.pdf?arnumber=9811663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:06:05Z","timestamp":1667516765000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811663\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811663","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}