{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:37:19Z","timestamp":1740101839547,"version":"3.37.3"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T00:00:00Z","timestamp":1680566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T00:00:00Z","timestamp":1680566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 109-2218-E-007-023"],"award-info":[{"award-number":["MOST 109-2218-E-007-023"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4,4]]},"DOI":"10.1109\/icit58465.2023.10143045","type":"proceedings-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T17:21:52Z","timestamp":1686331312000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["KeyState: Improving Image-based Reinforcement Learning with Keypoint for Robot Control"],"prefix":"10.1109","author":[{"given":"Ling-Chen","family":"Chen","sequence":"first","affiliation":[{"name":"National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Kai","family":"Ho","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Ta","family":"King","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Unsupervised learning of object landmarks through conditional image generation","volume":"31","author":"jakab","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","author":"shelhamer","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01121"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00285"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref30","first-page":"1539","article-title":"Unsupervised learning of visual 3d keypoints for control","author":"chen","year":"2021","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref11","article-title":"Deepmind control suite","author":"tassa","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"kostrikov","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Human learning in atari","author":"tsividis","year":"2017","journal-title":"Proceedings of the AAAI Spring Symposia"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00221"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00881"},{"key":"ref19","article-title":"Pves: Position-velocity encoders for unsupervised learning of structured state representations","author":"jonschkowski","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1890\/02-3114"},{"key":"ref24","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref20","first-page":"22171","article-title":"Reinforcement learning with latent flow","volume":"34","author":"shang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"End-to-end learning of keypoint representations for continuous control from images","author":"boney","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref29","article-title":"Unsupervised learning of object keypoints for perception and control","volume":"32","author":"kulkarni","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"laskin","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning Vienna Austria PMLR 119"},{"key":"ref7","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume":"33","author":"lee","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref3","article-title":"Model-based reinforcemenst learning for atari","author":"kaiser","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations 2020"},{"key":"ref5","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"Proceedings of the International Conference on Machine Learning"}],"event":{"name":"2023 IEEE International Conference on Industrial Technology (ICIT)","start":{"date-parts":[[2023,4,4]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2023,4,6]]}},"container-title":["2023 IEEE International Conference on Industrial Technology (ICIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10143075\/10143030\/10143045.pdf?arnumber=10143045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T17:59:21Z","timestamp":1687802361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10143045\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icit58465.2023.10143045","relation":{},"subject":[],"published":{"date-parts":[[2023,4,4]]}}}