{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:51:25Z","timestamp":1773377485277,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/isit.2019.8849765","type":"proceedings-article","created":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T21:46:12Z","timestamp":1569534372000},"page":"3062-3066","source":"Crossref","is-referenced-by-count":2,"title":["Maximum Likelihood Tensor Decomposition of Markov Decision Process"],"prefix":"10.1109","author":[{"given":"Chengzhuo","family":"Ni","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengdi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"496","article-title":"Linear programming for large-scale markov decision problems","volume":"32","author":"abbasi-yadkori","year":"2014","journal-title":"JMLR Workshop and Conference Proceedings"},{"key":"ref11","article-title":"Scalable bilinear pi learning using state and action features","author":"chen","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-200-7.50069-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6314781"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2141350"},{"key":"ref15","article-title":"Tensor decomposition and parallelization of markov decision processes","author":"smart","year":"2016","journal-title":"Ph D Dissertation"},{"key":"ref16","article-title":"Reinforcement learning of pomdps using spectral methods","author":"azizzadenesheli","year":"2016","journal-title":"Proceedings of the 29th Annual Conference on Learning Theory (COLT2016)"},{"key":"ref17","article-title":"Nuclear norm of higher-order tensors","author":"friedland","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2011.12.025"},{"key":"ref19","article-title":"Least-squares temporal difference learning","author":"boyan","year":"1999","journal-title":"Sixteenth International Conference on Machine Learning"},{"key":"ref4","article-title":"Reinforcement learning of pomdps using spectral methods","author":"azizzadenesheli","year":"2016"},{"key":"ref3","first-page":"361","article-title":"Reinforcement learning with soft state aggregation","author":"singh","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Spectral State Compression of Markov Processes","author":"zhang","year":"2018"},{"key":"ref5","first-page":"3033","article-title":"Estimation of Markov chain via rank-constrained likelihood","volume":"80","author":"li","year":"0"},{"key":"ref8","volume":"1","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"7907","DOI":"10.1073\/pnas.0707563105","article-title":"Optimal partition and effective dynamics of complex networks","volume":"105","author":"weinan","year":"2008","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref2","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1060.0188"},{"key":"ref20","article-title":"Primal-dual pi learning: Sample complexity and sublinear run time for ergodic markov decision problems","author":"wang","year":"2017"}],"event":{"name":"2019 IEEE International Symposium on Information Theory (ISIT)","location":"Paris, France","start":{"date-parts":[[2019,7,7]]},"end":{"date-parts":[[2019,7,12]]}},"container-title":["2019 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8827389\/8849208\/08849765.pdf?arnumber=8849765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:34:01Z","timestamp":1773347641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8849765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/isit.2019.8849765","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}