{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:35:26Z","timestamp":1776357326239,"version":"3.51.2"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1724257"],"award-info":[{"award-number":["IIS-1724257"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1724191"],"award-info":[{"award-number":["IIS-1724191"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1750649"],"award-info":[{"award-number":["IIS-1750649"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1830425"],"award-info":[{"award-number":["IIS-1830425"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1763878"],"award-info":[{"award-number":["IIS-1763878"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-19-1-2131"],"award-info":[{"award-number":["N00014-19-1-2131"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000104","name":"National Aeronautics and Space Administration","doi-asserted-by":"publisher","award":["80NSSC19K1474"],"award-info":[{"award-number":["80NSSC19K1474"]}],"id":[{"id":"10.13039\/100000104","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/tro.2020.2974093","type":"journal-article","created":{"date-parts":[[2020,3,3]],"date-time":"2020-03-03T22:08:03Z","timestamp":1583273283000},"page":"1067-1078","source":"Crossref","is-referenced-by-count":7,"title":["Learning Manipulation Skills via Hierarchical Spatial Attention"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7806-2186","authenticated-orcid":false,"given":"Marcus","family":"Gualtieri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Platt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225116"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202166"},{"key":"ref32","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"1243","article-title":"Learning to combine foveal glimpses with a third-order Boltzmann machine","author":"larochelle","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","article-title":"Source code for: Learning manipulation skills via HSA","year":"0"},{"key":"ref36","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968263"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793805"},{"key":"ref10","first-page":"173","article-title":"Learning hand-eye coordination for robotic grasping with large-scale data collection","author":"levine","year":"0","journal-title":"Proc Int Symp Exp Robot"},{"key":"ref40","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1177\/0278364917735594","article-title":"Grasp pose detection in point clouds","volume":"36","author":"pas","year":"2017","journal-title":"Int J Robot Res"},{"key":"ref13","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224581"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460553"},{"key":"ref19","first-page":"40","article-title":"Few-shot goal inference for visuomotor learning and planning","author":"xie","year":"2018","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref28","article-title":"Towards a unified theory of state abstraction for MDPs","author":"li","year":"0","journal-title":"Proc Int Symp Artif Intell Math"},{"key":"ref4","first-page":"8042","article-title":"Deictic image maps: An abstraction for learning pose invariant manipulation policies","author":"platt","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21236\/ADA276517"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1987.1087910"},{"key":"ref29","first-page":"1467","article-title":"Eye movements for reward maximization","author":"sprague","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","article-title":"Motion planning and the design of orienting devices for vibratory part feeders","author":"lozano-p\u00e9rez","year":"1986","journal-title":"MIT Artificial Intelligence Laboratory"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref7","first-page":"306","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","author":"tremblay","year":"0","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref2","first-page":"477","article-title":"Learning 6-DoF grasping and pick-place using attention focus","volume":"87","author":"gualtieri","year":"0","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058926"},{"key":"ref20","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","author":"james","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref21","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","article-title":"On-line Q-learning using connectionist systems","author":"rummery","year":"1994"},{"key":"ref23","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8860\/9159950\/9023569-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/9159950\/09023569.pdf?arnumber=9023569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T16:48:16Z","timestamp":1651078096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":40,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tro.2020.2974093","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8]]}}}