{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T02:10:17Z","timestamp":1783476617988,"version":"3.55.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"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":[[2020,10,11]]},"DOI":"10.1109\/smc42975.2020.9282951","type":"proceedings-article","created":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T21:44:48Z","timestamp":1607982288000},"page":"4066-4072","source":"Crossref","is-referenced-by-count":43,"title":["Learning Continuous Control Actions for Robotic Grasping with Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Asad Ali","family":"Shahid","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Loris","family":"Roveda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dario","family":"Piga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Braghin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref32","first-page":"833","article-title":"Reinforcement learning in continuous action spaces through sequential monte carlo methods","author":"lazaric","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref31","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref30","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref35","first-page":"767","article-title":"Surreal: Open-source reinforcement learning framework and robot manipulation benchmark","author":"fan","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref34","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980200"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref13","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015"},{"key":"ref14","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","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":"ref16","author":"deisenroth","year":"2013","journal-title":"A Survey on Policy Search for Robotics"},{"key":"ref17","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref18","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref4","first-page":"182","article-title":"Relative entropy inverse reinforcement learning","author":"boularias","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463191"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461076"},{"key":"ref6","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017"},{"key":"ref29","article-title":"Solving rubik’s cube with a robot hand","author":"akkaya","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649089"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912472380"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref9","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s12599-014-0334-4","article-title":"Industry 4.0","volume":"6","author":"lasi","year":"2014","journal-title":"Business & Information Systems Engineering"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref22","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref25","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","author":"james","year":"2017"}],"event":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Toronto, ON, Canada","start":{"date-parts":[[2020,10,11]]},"end":{"date-parts":[[2020,10,14]]}},"container-title":["2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9282733\/9282811\/09282951.pdf?arnumber=9282951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:15:55Z","timestamp":1656602155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9282951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,11]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/smc42975.2020.9282951","relation":{},"subject":[],"published":{"date-parts":[[2020,10,11]]}}}