{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:31:20Z","timestamp":1730205080638,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"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":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383754","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"6166-6171","source":"Crossref","is-referenced-by-count":0,"title":["Toward Understanding State Representation Learning in MuZero: A Case Study in Linear Quadratic Gaussian Control"],"prefix":"10.1109","author":[{"given":"Yi","family":"Tian","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Department of Electrical Engineering and Computer Science"}]},{"given":"Kaiqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Maryland,Department of Electrical and Computer Engineering,College Park"}]},{"given":"Russ","family":"Tedrake","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Department of Electrical Engineering and Computer Science"}]},{"given":"Suvrit","family":"Sra","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Department of Electrical Engineering and Computer Science"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Dynamic Programming and Optimal Control: Volume I","volume":"1","author":"Bertsekas","year":"2012"},{"key":"ref2","first-page":"3480","article-title":"Learning task informed abstractions","volume-title":"International Conference on Machine Learning","author":"Fu","year":"2021"},{"journal-title":"Dream to control: Learning behaviors by latent imagination","year":"2019","author":"Hafner","key":"ref3"},{"key":"ref4","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"International conference on machine learning","author":"Hafner","year":"2019"},{"journal-title":"Mastering Atari with discrete world models","year":"2020","author":"Hafner","key":"ref5"},{"journal-title":"Mastering diverse domains through world models","year":"2023","author":"Hafner","key":"ref6"},{"journal-title":"Time varying regression with hidden linear dynamics","year":"2021","author":"Jadbabaie","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/9.310049"},{"key":"ref9","first-page":"20876","article-title":"Logarithmic regret bound in partially observable linear dynamical systems","volume":"33","author":"Lale","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483309"},{"journal-title":"Guaranteed discovery of controllable latent states with multi-step inverse models","year":"2022","author":"Lamb","key":"ref11"},{"journal-title":"Playing Atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","article-title":"Value prediction network","volume":"30","author":"Oh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1142\/9789812772930_0009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref21","first-page":"439","article-title":"Learning without mixing: Towards a sharp analysis of linear system identification","volume-title":"Conference On Learning Theory","author":"Simchowitz","year":"2018"},{"key":"ref22","first-page":"2714","article-title":"Learning linear dynamical systems with semi-parametric least squares","volume-title":"Conference on Learning Theory","author":"Simchowitz","year":"2019"},{"journal-title":"Approximate information state for approximate planning and reinforcement learning in partially observed systems","year":"2020","author":"Subramanian","key":"ref23"},{"journal-title":"Can direct latent model learning solve linear quadratic Gaussian control?","year":"2022","author":"Zhang","key":"ref24"},{"key":"ref25","first-page":"25476","article-title":"Mastering Atari games with limited data","volume":"34","author":"Ye","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Learning invariant representations for reinforcement learning without reconstruction","year":"2020","author":"Zhang","key":"ref26"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383754.pdf?arnumber=10383754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:30:42Z","timestamp":1706027442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383754","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}