{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T18:26:41Z","timestamp":1729621601810,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,4]]},"DOI":"10.1109\/icnsc.2008.4525466","type":"proceedings-article","created":{"date-parts":[[2008,5,20]],"date-time":"2008-05-20T20:11:19Z","timestamp":1211314279000},"page":"1541-1546","source":"Crossref","is-referenced-by-count":3,"title":["Policy Gradient SMDP for Resource Allocation and Routing in Integrated Services Networks"],"prefix":"10.1109","author":[{"given":"Nguyen Hoang","family":"Viet","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngo Anh","family":"Vien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"TaeChoong","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/49.103545"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0089"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/49.824797"},{"journal-title":"Dynamic Programming and Optimal Control","year":"2001","author":"bertsekas","key":"15"},{"journal-title":"Applied Probability Models with Optimization Applications","year":"1970","author":"ross","key":"16"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.886173"},{"key":"14","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"infinite-horizon policy-gradient estimation","volume":"15","author":"baxter","year":"2001","journal-title":"Journal of Artifcial Intelligence Research (JAIR)"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2005.853408"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2006.02.023"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/190314.190330"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2005","author":"puterman","key":"3"},{"journal-title":"ANCLES User Manual","year":"1997","key":"20"},{"year":"0","key":"2"},{"journal-title":"High-Performance Communication Networks","year":"1996","author":"walrand","key":"1"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"7"},{"year":"0","key":"6"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2002.1014669"},{"journal-title":"Dynamic Programming and Optimal Control","year":"2005","author":"bertsekas","key":"4"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"9"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"}],"event":{"name":"2008 IEEE International Conference on Networking, Sensing and Control (ICNSC)","start":{"date-parts":[[2008,4,6]]},"location":"Sanya, China","end":{"date-parts":[[2008,4,8]]}},"container-title":["2008 IEEE International Conference on Networking, Sensing and Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4489617\/4525150\/04525466.pdf?arnumber=4525466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,11]],"date-time":"2019-05-11T15:00:44Z","timestamp":1557586844000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4525466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icnsc.2008.4525466","relation":{},"subject":[],"published":{"date-parts":[[2008,4]]}}}