{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T07:46:38Z","timestamp":1725435998927},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,9]]},"DOI":"10.1109\/allerton.2010.5707075","type":"proceedings-article","created":{"date-parts":[[2011,2,3]],"date-time":"2011-02-03T21:50:52Z","timestamp":1296769852000},"page":"1384-1390","source":"Crossref","is-referenced-by-count":0,"title":["Tutor learning using linear constraints in approximate dynamic programming"],"prefix":"10.1109","author":[{"given":"Dotan","family":"Di Castro","sequence":"first","affiliation":[]},{"given":"Shie","family":"Mannor","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0094"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.3.259"},{"journal-title":"Microeconomic Theory","year":"1995","author":"mas-colell","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5732-z"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(85)90317-8"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927528"},{"journal-title":"Dynamic Programming and Optimal Control","year":"2007","author":"bertsekas","key":"ref4"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1515\/9781400874668","author":"bellman","year":"1961","journal-title":"Adaptive Control Processes A Guided Tour"},{"journal-title":"Introduction to Linear Optimization","year":"1997","author":"bertsimas","key":"ref6"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.10.1.98"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)90015-3"},{"journal-title":"Dynamic Programming","year":"1957","author":"bellman","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/2584329"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.850.24925"}],"event":{"name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","start":{"date-parts":[[2010,9,29]]},"location":"Monticello, IL, USA","end":{"date-parts":[[2010,10,1]]}},"container-title":["2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5701578\/5706874\/05707075.pdf?arnumber=5707075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T14:01:28Z","timestamp":1637244088000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5707075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,9]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/allerton.2010.5707075","relation":{},"subject":[],"published":{"date-parts":[[2010,9]]}}}