{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:56:39Z","timestamp":1730303799433,"version":"3.28.0"},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1109\/vtcfall.2016.7881050","type":"proceedings-article","created":{"date-parts":[[2017,3,20]],"date-time":"2017-03-20T16:33:48Z","timestamp":1490027628000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Intelligent Traffic Signal Duration Adaptation Using Q-Learning with an Evolving State Space"],"prefix":"10.1109","author":[{"given":"Vinayak V.","family":"Gaikwad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanket S.","family":"Kadarkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav S.","family":"Kasbekar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2012.6362499"},{"journal-title":"Report for INRIX","article-title":"The future economic and environmental costs of gridlock in 2030","year":"2014","key":"ref11"},{"journal-title":"MATLAB Version 8 0 0 783","year":"2012","key":"ref12"},{"journal-title":"SUMO Version 0 25 0","year":"2015","key":"ref13"},{"key":"ref4","article-title":"Multi-Agent Reinforcement Learning for Integrated Network of Adaptive Traffic Light Controllers (MARLIN-ATSC)","author":"el-tantawy","year":"2012","journal-title":"Proc of IEEE 17th International Conference on Intelligent Transport System (ITSC)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/T-VT.1980.23833"},{"key":"ref5","article-title":"A Comprehensive Survey of Multiagent Reinforcement Learning","volume":"38","author":"lucian","year":"2008","journal-title":"IEEE Trans Systems Man and Cybernetics Part C Applications and Reviews"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref8"},{"journal-title":"Traffic Flow Fundamentals","year":"1990","author":"adolf","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6958095"},{"journal-title":"Reinforcement Learning An Introduction","year":"2012","author":"sutton","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ATNAC.2012.6398066"}],"event":{"name":"2016 IEEE 84th Vehicular Technology Conference (VTC-Fall)","start":{"date-parts":[[2016,9,18]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2016,9,21]]}},"container-title":["2016 IEEE 84th Vehicular Technology Conference (VTC-Fall)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7879553\/7880833\/07881050.pdf?arnumber=7881050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,31]],"date-time":"2017-03-31T18:13:14Z","timestamp":1490983994000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7881050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,9]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/vtcfall.2016.7881050","relation":{},"subject":[],"published":{"date-parts":[[2016,9]]}}}