{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:20:49Z","timestamp":1776183649176,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8593986","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"4238-4245","source":"Crossref","is-referenced-by-count":466,"title":["Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Andy","family":"Zeng","sequence":"first","affiliation":[]},{"given":"Shuran","family":"Song","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Welker","sequence":"additional","affiliation":[]},{"given":"Johnny","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Alberto","family":"Rodriguez","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Funkhouser","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","year":"0","journal-title":"Project webpage"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref33","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref37","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"ICLRE"},{"key":"ref36","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"ICML"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-leaming","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref34","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9306-z"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9378","article-title":"Learning to manipulate unknown objects in clutter by reinforcement","author":"boularias","year":"2015","journal-title":"AAAI"},{"key":"ref13","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2016","journal-title":"JMLR"},{"key":"ref14","author":"popov","year":"2017","journal-title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation"},{"key":"ref15","author":"rajeswaran","year":"2017","journal-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758091"},{"key":"ref17","article-title":"A convex polynomial force-motion model for planar sliding: Identification and application","author":"zhou","year":"2016","journal-title":"ICRA"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_29"},{"key":"ref28","author":"diankov","year":"2010","journal-title":"Automated Construction of Robotic Manipulation Programs"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989345"},{"key":"ref27","article-title":"Autonomous acquisition of pushing actions to support object grasping with a humanoid robot","author":"omr?en","year":"2009","journal-title":"Humanoids"},{"key":"ref3","article-title":"Feedback control of the pusher-slider system: A story of hybrid and underactuated contact dynamics","author":"hogan","year":"2016","journal-title":"WAFR"},{"key":"ref6","article-title":"Policy transfer via modularity","author":"ignasi","year":"2017","journal-title":"IROS"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref8","article-title":"Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching","author":"zeng","year":"2018","journal-title":"ICRA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0043-1648(91)90104-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759114"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500303"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224697"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152709"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912442972"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989165"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Madrid","start":{"date-parts":[[2018,10,1]]},"end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08593986.pdf?arnumber=8593986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T03:52:06Z","timestamp":1694577126000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8593986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8593986","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}