{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T06:29:09Z","timestamp":1725690549312},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053819","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"3672-3676","source":"Crossref","is-referenced-by-count":2,"title":["Disentangling Controllable Object Through Video Prediction Improves Visual Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yuanyi","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Schwing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref11","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"stadie","year":"2015","journal-title":"NIPS 2015 Workshop on Deep Reinforcement Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref14","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"2015","journal-title":"Neural Information Processing Systems"},{"key":"ref15","article-title":"A deep learning approach for joint video frame and reward prediction in atari games","author":"leibfried","year":"2016","journal-title":"ICML 2017 Workshop on Principled Approaches to Deep Learning"},{"key":"ref16","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref18","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Neural Information Processing Systems"},{"key":"ref19","article-title":"Investigating contingency awareness using atari 2600 games","author":"bellemare","year":"2012","journal-title":"AAAI"},{"year":"2019","key":"ref4","article-title":"AlphaStar: Mastering the Real-Time Strategy Game StarCraft II"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"year":"2019","key":"ref5"},{"key":"ref8","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"2016","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref7","article-title":"Independently controllable features","author":"thomas","year":"2017","journal-title":"Rldm"},{"article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","year":"2018","author":"ebert","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"ref9","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref20","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Neural Information Processing Systems"},{"key":"ref22","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"racani\u00e8re","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref21","article-title":"Contingency-aware exploration in reinforcement learning","author":"choi","year":"2019","journal-title":"ICLRE"},{"key":"ref24","article-title":"Model-based reinforcement learning for atari","author":"kaiser","year":"2020","journal-title":"ICLRE"},{"key":"ref23","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"International Conference on Machine Learning"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053819.pdf?arnumber=9053819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:21:36Z","timestamp":1656375696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053819","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}