{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T18:27:42Z","timestamp":1771525662863,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/lra.2023.3295236","type":"journal-article","created":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:53:14Z","timestamp":1689616394000},"page":"5480-5487","source":"Crossref","is-referenced-by-count":17,"title":["Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3643-0585","authenticated-orcid":false,"given":"Max","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0063-0905","authenticated-orcid":false,"given":"Yijiong","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4062-5959","authenticated-orcid":false,"given":"Alex","family":"Church","sequence":"additional","affiliation":[{"name":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5630-683X","authenticated-orcid":false,"given":"John","family":"Lloyd","sequence":"additional","affiliation":[{"name":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7649-7605","authenticated-orcid":false,"given":"Dandan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0595-4239","authenticated-orcid":false,"given":"David A.W.","family":"Barton","sequence":"additional","affiliation":[{"name":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5327-1523","authenticated-orcid":false,"given":"Nathan F.","family":"Lepora","sequence":"additional","affiliation":[{"name":"Department of Engineering Mathematics, Bristol Robotics Laboratory, University of Bristol, Bristol, U.K."}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2017.0052"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3190641"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3195195"},{"key":"ref34","first-page":"10376","article-title":"Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards","volume":"32","author":"trott","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500303"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2020.2979658"},{"key":"ref36","article-title":"Benchmarking in manipulation research: The YCB object and model set and benchmarking protocols","author":"calli","year":"2015"},{"key":"ref31","first-page":"1","article-title":"Stable-Baselines3: Reliable reinforcement learning implementations","volume":"22","author":"raffin","year":"2021","journal-title":"J Mach Learn Res"},{"key":"ref30","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","first-page":"1645","article-title":"Tactile sim-to-real policy transfer via real-to-sim image translation","author":"church","year":"0","journal-title":"Proc 5th Conf Robot Learn"},{"key":"ref33","article-title":"MBRL-LIB: A modular library for model-based reinforcement learning","author":"pineda","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3104471"},{"key":"ref32","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"chua","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"336","article-title":"A data-efficient approach to precise and controlled pushing","author":"bauza","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43089-4_51"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246918"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593995"},{"key":"ref19","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341076"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197512"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561646"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063925"},{"key":"ref25","first-page":"1015","article-title":"Tactile object pose estimation from the first touch with geometric contact rendering","author":"villalonga","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref20","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"ebert","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.829437"},{"key":"ref21","first-page":"9191","article-title":"Visual reinforcement learning with imagined goals","volume":"31","author":"nair","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142412"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146945"},{"key":"ref29","first-page":"1094","article-title":"Learning to Achieve Goals","volume":"2","author":"kaelbling","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9804-8"},{"key":"ref7","article-title":"Keypoints into the future: Self-supervised correspondence in model-based reinforcement learning","author":"manuelli","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1992.587370"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758091"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920954896"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967920"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10185095\/10182274.pdf?arnumber=10182274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T18:01:38Z","timestamp":1692036098000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10182274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":36,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3295236","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}