{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T04:49:44Z","timestamp":1774327784128,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610910","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5434-5440","source":"Crossref","is-referenced-by-count":2,"title":["Contact Energy Based Hindsight Experience Prioritization"],"prefix":"10.1109","author":[{"given":"Erdi","family":"Sayar","sequence":"first","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenshan","family":"Bing","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlo","family":"D\u2019Eramo","sequence":"additional","affiliation":[{"name":"University of Würzburg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ozgur S.","family":"Oguz","sequence":"additional","affiliation":[{"name":"Bilkent University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3204237"},{"key":"ref4","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3172754"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3088947"},{"key":"ref10","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"ICML","author":"Ng"},{"key":"ref11","article-title":"Hindsight experience replay","volume-title":"CoRR","volume":"abs\/1707.01495","author":"Andrychowicz","year":"2017"},{"key":"ref12","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref13","first-page":"7553","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Zhao"},{"key":"ref14","first-page":"113","article-title":"Energy-based hindsight experience prioritization","volume-title":"Conference on Robot Learning","author":"Zhao"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8793733"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iros45743.2020.9341006"},{"key":"ref17","article-title":"Tactile sensing and deep reinforcement learning for inhand manipulation tasks","volume-title":"IROS Workshop on Autonomous Object Manipulation","author":"Melnik"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3061308"},{"key":"ref19","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/smll.201600760"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2005.1626593"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593661"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9707-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852797"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2517244"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2162271"},{"key":"ref27","article-title":"New methods for active tactile object perception and learning with artificial robotic skin","volume-title":"Dissertation, Technische Universit\u00e4t M\u00fcnchen","author":"Kaboli","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363524"},{"key":"ref29","article-title":"Tactile grasp refinement using deep reinforcement learning and analytic grasp stability metrics","author":"Koenig","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892973"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.3139\/9783446466081","volume-title":"Deep reinforcement learning in action.","author":"Zai","year":"2020"},{"key":"ref32","article-title":"Universal value function approximators","volume-title":"ICML","author":"Schaul"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref34","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3270298"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160626"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26210"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341769"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref41","article-title":"Language-conditioned learning for robotic manipulation: A survey","author":"Zhou","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610910.pdf?arnumber=10610910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:22:53Z","timestamp":1723267373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610910","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}