{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:20:11Z","timestamp":1730204411403,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9029743","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T04:43:11Z","timestamp":1584074591000},"page":"1293-1300","source":"Crossref","is-referenced-by-count":0,"title":["Stochastic Primal-Dual Method for Learning Mixture Policies in Markov Decision Processes"],"prefix":"10.1109","author":[{"given":"Masoud Badiei","family":"Khuzani","sequence":"first","affiliation":[]},{"given":"Varun","family":"Vasudevan","sequence":"additional","affiliation":[]},{"given":"Hongyi","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Xing","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/060649021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(02)00231-6"},{"journal-title":"Convex Analysis","year":"2015","author":"rockafellar","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.850.24925"},{"article-title":"CVX: Matlab software for disciplined convex programming, version 2.1","year":"2014","author":"grant","key":"ref15"},{"article-title":"Scalable bilinear ? learning using state and action features","year":"2018","author":"chen","key":"ref4"},{"key":"ref3","first-page":"2503","article-title":"Trading regret for efficiency: online convex optimization with long term constraints","volume":"13","author":"mahdavi","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.3.259"},{"journal-title":"Dynamic Programming and Optimal Control","year":"1995","author":"bertsekas","key":"ref5"},{"article-title":"Primal-dual ? learning: Sample complexity and sublinear run time for ergodic Markov decision problems","year":"2017","author":"wang","key":"ref8"},{"key":"ref7","first-page":"496","article-title":"Linear programming for large-scale Markov decision problems","author":"abbasi-yadkori","year":"2014","journal-title":"JMLR Workshop and Conference Proceedings"},{"article-title":"Optimizing over a restricted policy class in Markov decision processes","year":"2018","author":"banijamali","key":"ref2"},{"article-title":"On sample complexity of projection-free primal-dual methods for learning mixture policies in Markov decision processes","year":"2019","author":"badiei khuzani","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/070708111"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","start":{"date-parts":[[2019,12,11]]},"location":"Nice, France","end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09029743.pdf?arnumber=9029743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:19:42Z","timestamp":1658261982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9029743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9029743","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}