{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T23:54:58Z","timestamp":1767830098866,"version":"3.49.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811735","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"6365-6371","source":"Crossref","is-referenced-by-count":11,"title":["A Hybrid Approach for Learning to Shift and Grasp with Elaborate Motion Primitives"],"prefix":"10.1109","author":[{"given":"Zohar","family":"Feldman","sequence":"first","affiliation":[{"name":"Bosch Center for Artificial Intelligence (BCAI)"}]},{"given":"Hanna","family":"Ziesche","sequence":"additional","affiliation":[{"name":"Bosch Center for Artificial Intelligence (BCAI)"}]},{"given":"Ngo Anh","family":"Vien","sequence":"additional","affiliation":[{"name":"Bosch Center for Artificial Intelligence (BCAI)"}]},{"given":"Dotan Di","family":"Castro","sequence":"additional","affiliation":[{"name":"Bosch Center for Artificial Intelligence (BCAI)"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref38","first-page":"1582","article-title":"Addressing function ap-proximation error in actor-critic methods","volume":"80","author":"fujimoto","year":"2018","journal-title":"ICML ser Proceedings of Machine Learning Research"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794143"},{"key":"ref32","article-title":"Learning to push by grasping: Using multiple tasks for effective learning","volume":"abs 1609 9025","author":"pinto","year":"2016","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9378"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9306-z"},{"key":"ref37","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"kostrikov","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref36","article-title":"Soft actor-critic algorithms and applications","volume":"abs 1812 5905","author":"haarnoja","year":"2018","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560901"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968042"},{"key":"ref10","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2013.6698839"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","article-title":"Data-driven grasp synthesis-a survey","volume":"30","author":"bohg","year":"2014","journal-title":"IEEE Transactions on Robotics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202237"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859066"},{"key":"ref17","article-title":"Antipodal robotic grasping using generative residual convolutional neural network","volume":"abs 1909 4810","author":"kumra","year":"2019","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487342"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004787"},{"key":"ref4","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197415"},{"key":"ref3","author":"chryssolouris","year":"2013","journal-title":"Manufacturing systems Theory and practice"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref5","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref8","first-page":"735","article-title":"Continuous-discrete reinforcement learning for hybrid control in robotics","author":"neunert","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref2","author":"maynard","year":"2001","journal-title":"Maynard's Industrial Engineering Handbook"},{"key":"ref9","article-title":"Discrete and continuous action representation for practical rl in video games","author":"delalleau","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463204"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00299"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968042"},{"key":"ref24","article-title":"Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours","volume":"abs 1509 6825","author":"pinto","year":"2015","journal-title":"CoRR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref26","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume":"abs 1806 10293","author":"kalashnikov","year":"2018","journal-title":"CoRR"},{"key":"ref25","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","volume":"abs 1603 2199","author":"levine","year":"2016","journal-title":"CoRR"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811735.pdf?arnumber=9811735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:08:44Z","timestamp":1667516924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811735\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811735","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}