{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:45:20Z","timestamp":1774161920414,"version":"3.50.1"},"reference-count":28,"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\/iros51168.2021.9635936","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"190-197","source":"Crossref","is-referenced-by-count":5,"title":["Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces"],"prefix":"10.1109","author":[{"given":"Nicolo","family":"Botteghi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khaled","family":"Alaa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mannes","family":"Poel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beril","family":"Sirmacek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Brune","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abeje","family":"Mersha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Stramigioli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics","author":"raffin","year":"2019","journal-title":"In International Conference on Learning Representations Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref16","article-title":"Stable reinforcement learning with autoencoders for tactile and visual data","volume":"2019","author":"hoof","year":"2016","journal-title":"Monet Unsupervised scene decomposition and representation"},{"key":"ref17","article-title":"Plannable approximations to MDP homomorphisms: Equivariance under actions","author":"van der","year":"2020","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref18","article-title":"Deepmdp: Learning continuous latent space models for representation learning","author":"gelada","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Learning invariant representations for reinforcement learning without reconstruction","author":"zhang","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref4","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Deep Learning Workshop International Conference on Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-015-0356-1"},{"key":"ref3","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/robotics2030122"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref2","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","article-title":"Combined reinforcement learning via abstract representations","author":"fran\u00e7ois-lavet","year":"2019","journal-title":"International Conference on Artificial Intelligence"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref21","article-title":"Low Dimensional State Representation Learning with Reward-shaped Priors","author":"botteghi","year":"2020","journal-title":"International Conference on Pattern Recognition"},{"key":"ref24","author":"jonschkowski","year":"2017","journal-title":"Pves Position-velocity encoders for unsupervised learning of structured state representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLII-2-W13-857-2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967938"},{"key":"ref25","author":"lesort","year":"2017","journal-title":"Unsupervised state representation learning with robotic priors a robustness benchmark"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"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\/09635936.pdf?arnumber=9635936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:39Z","timestamp":1652201679000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9635936\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9635936","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}