{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:42:40Z","timestamp":1730270560393,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9635931","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T15:45:38Z","timestamp":1639669538000},"page":"198-205","source":"Crossref","is-referenced-by-count":6,"title":["Acceleration of Actor-Critic Deep Reinforcement Learning for Visual Grasping by State Representation Learning Based on a Preprocessed Input Image"],"prefix":"10.1109","author":[{"given":"Taewon","family":"Kim","sequence":"first","affiliation":[]},{"given":"Yeseong","family":"Park","sequence":"additional","affiliation":[]},{"given":"Youngbin","family":"Park","sequence":"additional","affiliation":[]},{"given":"Sang Hyoung","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Il","family":"Hong Suh","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Stochastic latent actor-critic Deep reinforcement learning with a latent variable model","year":"2019","author":"lee","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794126"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref10","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume":"87","author":"kalashnikov","year":"2018","journal-title":"PMLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref13","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"ICLRE"},{"key":"ref14","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"NIPS"},{"key":"ref15","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"NIPS"},{"key":"ref16","article-title":"Incremental slow feature analysis: Adaptive and episodic learning from high-dimensional input streams","volume":"abs 1112 2113","author":"kompella","year":"2011","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"ref18","article-title":"Learning visual servoing with deep features and fitted Q-iteration","author":"lee","year":"2017","journal-title":"ICLRE"},{"key":"ref19","article-title":"SOLAR: Deep structured representations for model-based reinforcement learning","author":"zhang","year":"2019","journal-title":"ICML"},{"journal-title":"YOLOv3 An Incremental Improvement","year":"2018","author":"redmon","key":"ref28"},{"key":"ref4","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"year":"0","key":"ref27"},{"key":"ref3","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"journal-title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","year":"2017","author":"popov","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"ref7","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460887"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref1","article-title":"Learning hand-eye coordination for robotic grasping with large-scale data collection","author":"levine","year":"2016","journal-title":"International Symposium on Experimental Robotics"},{"key":"ref20","article-title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","author":"van steenkiste","year":"2019","journal-title":"Advances in neural information processing systems"},{"journal-title":"Auto-encoding variational bayes","year":"2013","author":"kingma","key":"ref22"},{"key":"ref21","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1038\/26475","article-title":"Object-based attention in the primary visual cortex of the macaque monkey","volume":"395","author":"roelfsema","year":"1998","journal-title":"Nature"},{"key":"ref23","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"ICLRE"},{"key":"ref26","first-page":"2016","article-title":"PyBullet, a Python module for physics simulation, games, robotics and machine learning","author":"coumans","year":"0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(92)90344-8"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2021,9,27]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09635931.pdf?arnumber=9635931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:54:46Z","timestamp":1652187286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9635931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9635931","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}