{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:03:19Z","timestamp":1777636999496,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"publisher","award":["RL-2016-39"],"award-info":[{"award-number":["RL-2016-39"]}],"id":[{"id":"10.13039\/501100000275","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EPSRC CASE Award"},{"name":"Google DeepMind"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/lra.2020.3010461","type":"journal-article","created":{"date-parts":[[2020,7,20]],"date-time":"2020-07-20T21:06:10Z","timestamp":1595279170000},"page":"6145-6152","source":"Crossref","is-referenced-by-count":29,"title":["Deep Reinforcement Learning for Tactile Robotics: Learning to Type on a Braille Keyboard"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4062-5959","authenticated-orcid":false,"given":"Alex","family":"Church","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5630-683X","authenticated-orcid":false,"given":"John","family":"Lloyd","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raia","family":"Hadsell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5327-1523","authenticated-orcid":false,"given":"Nathan F.","family":"Lepora","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Prioritized experience replay","author":"schaul","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref38","article-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"popov","year":"2017","journal-title":"arXiv 1704 03073"},{"key":"ref33","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":"ref32","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref30","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"wang","year":"0","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref36","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"0","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref35","first-page":"3215","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref34","article-title":"Maximum a posteriori policy optimisation","author":"abdolmaleki","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref10","first-page":"561","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","volume":"87","author":"mahmood","year":"0","journal-title":"Proc 2nd Conf Robot Lear"},{"key":"ref40","first-page":"142","article-title":"MAT: Multi-fingered adaptive tactile grasping via deep reinforcement learning","volume":"100","author":"wu","year":"0","journal-title":"Proc Annu Conf Robot Learn"},{"key":"ref11","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":"ref12","first-page":"1582","article-title":"Addressing function approximation error in Actor-Critic methods","author":"fujimoto","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","article-title":"Soft Actor-Critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv 1812 05905"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref15","first-page":"3","article-title":"Learning dexterous in-hand manipulation","volume":"39","author":"openai","year":"2018","journal-title":"Int J Robot Res"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref17","article-title":"Solving Rubik's cube with a robot hand","author":"openai","year":"2019","journal-title":"arXiv 1910 07113"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759309"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2017.0052"},{"key":"ref4","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018","journal-title":"arXiv 1802 09464"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2020.2979658"},{"key":"ref3","article-title":"DeepMind control suite","author":"tassa","year":"2018","journal-title":"arXiv 1801 00690"},{"key":"ref6","first-page":"1300","article-title":"ROBEL: Robotics benchmarks for learning with low-cost robots","volume":"100","author":"ahn","year":"0","journal-title":"Proc Annu Conf Robot Learn"},{"key":"ref29","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Annual Conf Neural Inf Process Syst"},{"key":"ref5","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794390"},{"key":"ref7","article-title":"OffWorld gym: Open-access physical robotics environment for real-world reinforcement learning benchmark and research","author":"kumar","year":"2019","journal-title":"arXiv 1910 08639"},{"key":"ref2","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","first-page":"4635","article-title":"Setting up a reinforcement learning task with a real-world robot","author":"mahmood","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref20","article-title":"Learning gentle object manipulation with curiosity-driven deep reinforcement learning","author":"huang","year":"2019","journal-title":"arXiv 1903 08542"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899192"},{"key":"ref21","article-title":"Surface following using deep reinforcement learning and a GelSightTactile sensor","author":"lu","year":"2019","journal-title":"arXiv 1912 00745"},{"key":"ref24","first-page":"314","article-title":"The feeling of success: Does touch sensing help predict grasp outcomes?","volume":"78","author":"calandra","year":"0","journal-title":"Proc 1st Conf Robot Learn"},{"key":"ref23","article-title":"Shape-independent hardness estimation using deep learning and a gelsight tactile sensor","volume":"17","author":"yuan","year":"2017","journal-title":"SENSORS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593528"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852779"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9133350\/09144378.pdf?arnumber=9144378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:33:44Z","timestamp":1651080824000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9144378\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":40,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.3010461","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}