{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:32:02Z","timestamp":1792593122505,"version":"4.5.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197508","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"2543-2549","source":"Crossref","is-referenced-by-count":29,"title":["Grasp for Stacking via Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Junhao","family":"Zhang","sequence":"first","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibin","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1145\/3197517.3201311","article-title":"Deepmimic: Example-guided deep reinforcement learning of physics-based character skills","volume":"37","author":"peng","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022620604568"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087172"},{"key":"ref37","article-title":"Network in network","author":"lin","year":"2013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"Grasp2vec: Learning object representations from self-supervised grasping","author":"jang","year":"2018"},{"key":"ref34","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":"ref10","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"6284","DOI":"10.1109\/ICRA.2018.8461039","article-title":"Deep reinforcement learning for vision-based robotic grasping: A simulated comparative evaluation of off-policy methods","author":"quillen","year":"2018","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"4238","DOI":"10.1109\/IROS.2018.8593986","article-title":"Learning synergies between pushing and grasping with self-supervised deep reinforcement learning","author":"zeng","year":"2018","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224581"},{"key":"ref15","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354683"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_29"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509508"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008090503603"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/13506280042000144"},{"key":"ref3","first-page":"544","article-title":"The mechanics of manipulation","volume":"2","author":"mason","year":"1985","journal-title":"Proceedings IEEE International Conference on Robotics and Automation"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2009.5379539"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202237"},{"key":"ref2","article-title":"Automated robot picking system for e-commerce fulfillment warehouse application","author":"liang","year":"2015","journal-title":"The 14th IFToMM World Congress"},{"key":"ref1","article-title":"Learning a visuomotor controller for real world robotic grasping using simulated depth images","author":"viereck","year":"2017"},{"key":"ref9","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224697"},{"key":"ref22","article-title":"Dexnet 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics","author":"mahler","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487342"},{"key":"ref24","first-page":"1551","article-title":"Learning to grasp everyday objects using reinforcement-learning with automatic value cut-off","author":"baier-lowenstein","year":"2007","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"ref42","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"sohn","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1805","DOI":"10.1109\/IROS40897.2019.8968278","article-title":"Learning actions from human demonstration video for robotic manipulation","author":"yang","year":"2019","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008874725911"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197508.pdf?arnumber=9197508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:43:00Z","timestamp":1756154580000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197508","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}