{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:25:31Z","timestamp":1756995931666,"version":"3.37.3"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004405","name":"Toyota Motor Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004405","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341605","type":"proceedings-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:26:48Z","timestamp":1613183208000},"page":"9712-9719","source":"Crossref","is-referenced-by-count":12,"title":["Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators"],"prefix":"10.1109","author":[{"given":"Yasuhiro","family":"Fujita","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kota","family":"Uenishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avinash","family":"Ummadisingu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prabhat","family":"Nagarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shimpei","family":"Masuda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mario Ynocente","family":"Castro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"422","article-title":"Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions","volume":"87","author":"cheng","year":"2018","journal-title":"CoRL"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2016.7866521"},{"key":"ref33","article-title":"Robustness via retrying: Closed-loop robotic manipulation with self-supervised learning","author":"ebert","year":"2018","journal-title":"CoRL"},{"key":"ref32","article-title":"Grasp2Vec: Learning Object Representations from Self-Supervised Grasping","author":"jang","year":"2018","journal-title":"CoRL"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794143"},{"article-title":"Object Finding in Cluttered Scenes Using Interactive Perception","year":"2019","author":"novkovic","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139782"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92040-5_19"},{"key":"ref40","article-title":"Massively Parallel Methods for Deep Reinforcement Learning","author":"nair","year":"2015","journal-title":"Deep Learning Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"ref12","article-title":"Revisiting Distributed Synchronous SGD","author":"chen","year":"2016","journal-title":"ICLR Workshop Track"},{"article-title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","year":"2017","author":"goyal","key":"ref13"},{"key":"ref14","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11791","article-title":"Distributional Reinforcement Learning With Quan-tile Regression","author":"dabney","year":"2018","journal-title":"AAAI"},{"key":"ref16","article-title":"Scalable, Distributed Data Structures for Internet Service Construction","volume":"4","author":"gribble","year":"2000","journal-title":"Proceedings of the 4th conference on Symposium on Operating System Design & Implementation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3149.214121"},{"key":"ref18","article-title":"Universal Value Function Approximators","author":"schaul","year":"2015","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94042-7_7"},{"key":"ref28","article-title":"Visualizing and Understanding Atari Agents","author":"greydanus","year":"2018","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970622"},{"key":"ref27","article-title":"ChainerRL: A Deep Reinforcement Learning Library","author":"fujita","year":"2019","journal-title":"NeurIPS Workshop on Deep Reinforcement Learning"},{"key":"ref3","article-title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","author":"kalashnikov","year":"2018","journal-title":"CoRL"},{"article-title":"Solving Rubik’s Cube with a Robot Hand","year":"2019","author":"akkaya","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref8","article-title":"Hindsight Experience Replay","author":"andrychowicz","year":"2017","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Dota 2 with Large Scale Deep Reinforcement Learning","author":"berner","year":"2019","journal-title":"NeurIPS Workshop on Deep Reinforcement Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref9","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":"ref1","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":"ref20","article-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","author":"espeholt","year":"2018","journal-title":"ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1186\/s40648-019-0132-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.037"},{"key":"ref24","article-title":"ShapeNet: An Information-Rich 3D Model Repository","author":"chang","year":"2015","journal-title":"Stanford University — Princeton University — Toyota Technological Institute at Chicago Tech Rep"},{"key":"ref41","article-title":"rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch","author":"stooke","year":"2019","journal-title":"NeurIPS Workshop on Deep Reinforcement Learning"},{"article-title":"PyBullet, a Python module for physics simulation for games, robotics and machine learning","year":"2016","author":"coumans","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2020,10,24]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341605.pdf?arnumber=9341605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T04:15:17Z","timestamp":1671250517000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341605","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}