{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:09:38Z","timestamp":1791486578124,"version":"4.3.4"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Dyson Technology Ltd."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2974707","type":"journal-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T16:23:37Z","timestamp":1582043017000},"page":"3019-3026","source":"Crossref","is-referenced-by-count":369,"title":["RLBench: The Robot Learning Benchmark & Learning Environment"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3991-0621","authenticated-orcid":false,"given":"Stephen","family":"James","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zicong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David Rovick","family":"Arrojo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew J.","family":"Davison","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2953663"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref32","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968029"},{"key":"ref30","article-title":"RoboNet: Large-Scale Multi-Robot Learning","author":"dasari","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref37","first-page":"987","article-title":"Grasping unknown objects using an early cognitive vision system for general scene understanding","author":"popovi?","year":"0","journal-title":"Proc Int Conf Intell Robots Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094894"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906903"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989545"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463191"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1075\/is.10.3.06wis","article-title":"Robocup@ home: Scientific competition and benchmarking for domestic service robots","volume":"10","author":"wisspeintner","year":"2009","journal-title":"Interact Stud"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref22","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref21","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","article-title":"RoboNet: Large-scale multi-robot learning","author":"dasari","year":"2019","journal-title":"arXiv 1910 11215"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref26","article-title":"Lessons from the amazon picking challenge: Four aspects of building robotic systems","volume":"12","author":"eppner","year":"0","journal-title":"Proc Robot Sci Syst"},{"key":"ref25","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"2019"},{"key":"ref50","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","volume":"78","author":"james","year":"2018","journal-title":"Proc Conf Robot Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00015"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"ref56","article-title":"FutureMapping: The computational structure of spatial AI systems","author":"davison","year":"2018","journal-title":"arXiv 1803 11288"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref52","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume":"87","author":"matas","year":"2018","journal-title":"Proc Conf Robot Learn"},{"key":"ref10","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref11","article-title":"Deepmind control suite","author":"tassa","year":"2018","journal-title":"arXiv 1801 00690"},{"key":"ref40","article-title":"Bullet real-time physics simulation","author":"coumans","year":"2013"},{"key":"ref12","article-title":"Pyrep: Bringing v-rep to deep robot learning","author":"james","year":"0","journal-title":"arXiv 1906 11176"},{"key":"ref13","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":"ref14","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref16","article-title":"Alphastar: Mastering the real-time strategy game starcraft ii","year":"2019"},{"key":"ref17","article-title":"Openai five","year":"2018"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"arXiv 1806 10293"},{"key":"ref3","article-title":"3D simulation for robot arm control with deep q-learning","author":"james","year":"0","journal-title":"Proc Workshop Conf Neural Inf Syst Deep Learn Action and Interact"},{"key":"ref6","first-page":"783","article-title":"Task-embedded control networks for few-shot imitation learning","volume":"87","author":"james","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref5","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","volume":"78","author":"finn","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref49","article-title":"Meta-learning with latent embedding optimization","author":"rusu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","article-title":"Learning an embedding space for transferable robot skills","author":"hausman","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","first-page":"3637","article-title":"Matching networks for one shot learning","author":"vinyals","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref45","article-title":"A simple neural attentive meta-learner","author":"mishra","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref48","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2205651"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref44","article-title":"Rl$^2$: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016","journal-title":"arXiv 1611 02779"},{"key":"ref43","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","author":"santoro","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/09001253.pdf?arnumber=9001253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:32:35Z","timestamp":1651066355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9001253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":58,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2974707","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}