{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T14:04:30Z","timestamp":1758809070495,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"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":[[2019,4]]},"DOI":"10.1109\/infocom.2019.8737552","type":"proceedings-article","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T00:35:56Z","timestamp":1560818156000},"page":"127-135","source":"Crossref","is-referenced-by-count":4,"title":["Optimal Trunk-Reservation by Policy Learning"],"prefix":"10.1109","author":[{"given":"Antonio","family":"Massaro","sequence":"first","affiliation":[]},{"given":"Francesco","family":"De Pellegrini","sequence":"additional","affiliation":[]},{"given":"Lorenzo","family":"Maggi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref11","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/9.256332"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485847"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1998.760738"},{"key":"ref15","first-page":"209","article-title":"Adaptive call admission control under quality of service constraints: a reinforcement learning solution","volume":"18","author":"tong","year":"2000","journal-title":"IEEE JSAC"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1239\/aap\/1143936147"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/S0269964800003570"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref5","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"journal-title":"Extended Version Optimal Trunk-Reservation by Policy Learning","year":"2018","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.16.3.234"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"}],"event":{"name":"IEEE INFOCOM 2019 - IEEE Conference on Computer Communications","start":{"date-parts":[[2019,4,29]]},"location":"Paris, France","end":{"date-parts":[[2019,5,2]]}},"container-title":["IEEE INFOCOM 2019 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8732929\/8737365\/08737552.pdf?arnumber=8737552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:09:44Z","timestamp":1657854584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8737552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/infocom.2019.8737552","relation":{},"subject":[],"published":{"date-parts":[[2019,4]]}}}