{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:40:49Z","timestamp":1765546849381,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005049","name":"Science and Engineering Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561187","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"4274-4280","source":"Crossref","is-referenced-by-count":20,"title":["Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Kaiqi","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yong","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Harold","family":"Soh","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"robosuite: A modular simulation framework and benchmark for robot learning","year":"2020","author":"zhu","key":"ref10"},{"key":"ref11","article-title":"A new approach to linear filtering and prediction problems","author":"kalman","year":"1960","journal-title":"Journal of Fluids Engineering"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1986.1165342"},{"article-title":"Probabilistic robotics","year":"2005","author":"thrun","key":"ref13"},{"journal-title":"An Introduction to Probabilistic Graphical Models","year":"2003","author":"jordan","key":"ref14"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/0022-247X(65)90154-X","article-title":"Optimal control of markov processes with incomplete state information","volume":"10","author":"astrom","year":"1965","journal-title":"Journal of Mathematical Analysis and Applications"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref17","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"Int Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.020"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v34i06.6597","article-title":"Factorized inference in deep markov models for incomplete multimodal time series","author":"zhi-xuan","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref3","first-page":"5575","article-title":"Multimodal generative models for scalable weakly-supervised learning","author":"wu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA48506.2021.9561187","article-title":"Multi-modal mutual information (mummi) training for robust self-supervised deep reinforcement learning: Online appendix","author":"chen","year":"2021"},{"article-title":"Dream to control: Learning behaviors by latent imagination","year":"2019","author":"hafner","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"oord","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.103312"},{"article-title":"Contrastive variational model-based reinforcement learning for complex observations","year":"2020","author":"ma","key":"ref9"},{"article-title":"dm_control: Software and tasks for continuous control","year":"2020","author":"tassa","key":"ref20"},{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"haarnoja","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561187.pdf?arnumber=9561187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:53:38Z","timestamp":1673564018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561187","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}