{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T22:42:55Z","timestamp":1772750575016,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412421","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"3736-3743","source":"Crossref","is-referenced-by-count":3,"title":["Low Dimensional State Representation Learning with Reward-shaped Priors"],"prefix":"10.1109","author":[{"given":"Nicolo","family":"Botteghi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruben","family":"Obbink","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daan","family":"Geijs","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","author":"goroshin","year":"2015","journal-title":"Learning to linearize under uncertainty"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref12","author":"jonschkowski","year":"2017","journal-title":"Pves Position-velocity encoders for unsupervised learning of structured state representations"},{"key":"ref13","author":"agrawal","year":"2016","journal-title":"Learning to poke by poking Experiential learning of intuitive physics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967938"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-015-0356-1"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref17","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref18","article-title":"Reinforcement learning for robots using neural networks","author":"lin","year":"1993","journal-title":"Tech Rep"},{"key":"ref19","author":"van hasselt","year":"2016","journal-title":"Deep reinforcement learning with double q-learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref6","article-title":"Deep spatial autoencorders for visuomotor learning","author":"finn","year":"2015","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref8","author":"lesort","year":"2017","journal-title":"Unsu-pervised state representation learning with robotic priors a robustness benchmark"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34500-5_16"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080408"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref21","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412421.pdf?arnumber=9412421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:56Z","timestamp":1652197256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412421","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}