{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:48:18Z","timestamp":1740181698187,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"am","delay-in-days":0,"URL":"http:\/\/www.ieee.org\/publications_standards\/publications\/rights\/ieeecopyrightform.pdf"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.ieee.org\/publications_standards\/publications\/rights\/ieeecopyrightform.pdf"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["EPCN:1603861","CIF:AF:2008130"],"award-info":[{"award-number":["EPCN:1603861","CIF:AF:2008130"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/jsait.2021.3073257","type":"journal-article","created":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T20:31:26Z","timestamp":1618605086000},"page":"641-651","source":"Crossref","is-referenced-by-count":0,"title":["Empirical Policy Evaluation With Supergraphs"],"prefix":"10.1109","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2426-5604","authenticated-orcid":false,"given":"Daniel","family":"Vial","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9136-6419","authenticated-orcid":false,"given":"Vijay","family":"Subramanian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511581274"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2008.10129302"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835823"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2006.44"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2006.10129116"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775191"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3366635"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098072"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403108"},{"key":"ref18","first-page":"1423","article-title":"Fast bidirectional probability estimation in Markov models","author":"banerjee","year":"2015","journal-title":"Advances in neural information processing systems"},{"journal-title":"Rate Limiting","year":"2020","key":"ref19"},{"key":"ref28","first-page":"1","article-title":"Online-to-confidence-set conversions and application to sparse stochastic bandits","author":"abbasi-yadkori","year":"2012","journal-title":"Proc 15th Int Conf Artif Intell Stat"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974263"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3233\/IA-150080"},{"key":"ref3","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref6","first-page":"1","article-title":"Recall traces: Backtracking models for efficient reinforcement learning","author":"goyal","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"journal-title":"Personalized pagerank to a target node","year":"2013","author":"lofgren","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2015.0733"},{"key":"ref8","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"Proc Conf Robot Learn"},{"journal-title":"Forward-Backward Reinforcement Learning","year":"2018","author":"edwards","key":"ref7"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref2"},{"article-title":"The PageRank citation ranking: Bringing order to the Web","year":"1999","author":"page","key":"ref9"},{"journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL","year":"2019","author":"bertsekas","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5368-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04483-5_2"},{"key":"ref21","first-page":"5192","article-title":"Near-optimal time and sample complexities for solving Markov decision processes with a generative model","author":"sidford","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref24","first-page":"1177","article-title":"Finite-sample analysis of lasso-TD","author":"ghavamzadeh","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"89","article-title":"$l_{1}$\n-penalized projected Bellman residual","author":"geist","year":"2011","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553442"},{"key":"ref25","first-page":"102","article-title":"Regularized least squares temporal difference learning with nested $l_{2}$\n and $l_{1}$\n penalization","author":"hoffman","year":"2011","journal-title":"Proc of European Workshop on Reinforcement Learning"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/9459757\/9406112-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/9459757\/09406112.pdf?arnumber=9406112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T22:36:24Z","timestamp":1636410984000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9406112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":30,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2021.3073257","relation":{},"ISSN":["2641-8770"],"issn-type":[{"type":"electronic","value":"2641-8770"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}