{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:11:30Z","timestamp":1756995090306,"version":"3.28.0"},"reference-count":26,"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\/icra46639.2022.9812251","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T15:36:40Z","timestamp":1657640200000},"page":"8245-8251","source":"Crossref","is-referenced-by-count":2,"title":["Learning Multi-step Robotic Manipulation Policies from Visual Observation of Scene and Q-value Predictions of Previous Action"],"prefix":"10.1109","author":[{"given":"Sulabh","family":"Kumra","sequence":"first","affiliation":[{"name":"Rochester Institute of Technology,Rochester,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shirin","family":"Joshi","sequence":"additional","affiliation":[{"name":"Siemens Corporation, Corporate Technology,Berkeley,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ferat","family":"Sahin","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology,Rochester,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref11","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","author":"riedmiller","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216986"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3015448"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197326"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915594244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463204"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197331"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202237"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/027836490302210009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref1","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":"2013","journal-title":"IEEE Transactions on Robotics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3129833"},{"key":"ref21","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","author":"zeng","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00446"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.11.012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196733"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2022,5,23]]},"location":"Philadelphia, PA, USA","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\/09812251.pdf?arnumber=9812251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T19:05:44Z","timestamp":1667502344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812251","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}