{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:19:30Z","timestamp":1787012370981,"version":"3.56.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561232","type":"proceedings-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T20:28:35Z","timestamp":1634675315000},"page":"6650-6656","source":"Crossref","is-referenced-by-count":36,"title":["LASER: Learning a Latent Action Space for Efficient Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Arthur","family":"Allshire","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Martin-Martin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shawn","family":"Manuel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"},{"key":"ref32","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","author":"baldi","year":"2012","journal-title":"Proceedings of ICML Workshop on Unsupervised and Transfer Learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1"},{"key":"ref30","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref36","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018"},{"key":"ref35","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"zhu","year":"2020"},{"key":"ref34","first-page":"6","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume":"2","author":"higgins","year":"2017","journal-title":"ICLRE"},{"key":"ref10","article-title":"Learning compliance adaptation in contact-rich manipulation","author":"gao","year":"2020","journal-title":"Proc Int Conf Robotics and Automation (ICRA)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246874"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911402527"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916648389"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45622-8_16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36755-1_25"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7982","article-title":"Autonomous skill acquisition on a mobile manipulator","author":"konidaris","year":"2011","journal-title":"Twenty-Fifth AAAI Conference on Artificial Intelligence"},{"key":"ref19","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1981.4308708"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref27","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016"},{"key":"ref6","article-title":"Compliant motion programming: The task frame formalism revisited","author":"kr\u00f6ger","year":"2004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref29","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967946"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140713"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/70.508440"},{"key":"ref1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"JMLR"},{"key":"ref9","article-title":"Learning variable impedance control for contact sensitive tasks","author":"bogdanovic","year":"2019"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10916","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref22","article-title":"Dynamics learning with cascaded variational inference for multi-step manipulation","author":"fang","year":"2019","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917743319"},{"key":"ref24","first-page":"1431","article-title":"Plannable approximations to mdp homomorphisms: Equivariance under actions","author":"van der pol","year":"2020","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref23","article-title":"Dynamics-aware embeddings","author":"whitney","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref26","article-title":"Controlling assistive robots with learned latent actions","author":"losey","year":"2019"},{"key":"ref25","first-page":"941","article-title":"Learning action representations for reinforcement learning","author":"chandak","year":"2019","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561232.pdf?arnumber=9561232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T17:48:43Z","timestamp":1673545723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561232","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}