{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T06:05:13Z","timestamp":1760853913359,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2016,11,1]],"date-time":"2016-11-01T00:00:00Z","timestamp":1477958400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,11,1]],"date-time":"2016-11-01T00:00:00Z","timestamp":1477958400000},"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":[[2016,11]]},"DOI":"10.1109\/itsc.2016.7795890","type":"proceedings-article","created":{"date-parts":[[2016,12,26]],"date-time":"2016-12-26T21:45:07Z","timestamp":1482788707000},"page":"2065-2070","source":"Crossref","is-referenced-by-count":24,"title":["Towards autonomic urban traffic control with collaborative multi-policy reinforcement learning"],"prefix":"10.1109","author":[{"given":"Ivana","family":"Dusparic","sequence":"first","affiliation":[{"name":"School of Computer Science and Statistics, Trinity College Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Monteil","sequence":"additional","affiliation":[{"name":"School of Computer Science and Statistics, Trinity College Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinny","family":"Cahill","sequence":"additional","affiliation":[{"name":"School of Computer Science and Statistics, Trinity College Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Action selection methods using reinforcement learning","author":"humphrys","year":"1996","journal-title":"Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1023\/A:1022676722315","article-title":"Technical note: Q-Iearning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref23","first-page":"2298","article-title":"Accel-erating learning in multi-objective systems through transfer learning","author":"taylor","year":"2014","journal-title":"IJCNN 2014 Beijing"},{"key":"ref15","article-title":"SCATS: The sydney co-ordinated adaptive traffic system - principles, methodology, algorithms","author":"lowrie","year":"1982","journal-title":"Proceedings of the IEE International Conference on Road Traffic Signalling"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SusTech.2013.6617303"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6142-6_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.01.007"},{"key":"ref22","article-title":"P-marl: Prediction-based multi-agent reinforcement learning for non-stationary environments","author":"marinescu","year":"2015","journal-title":"AAMAS ' ‘12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"journal-title":"scoot-ute com","article-title":"Scoot","year":"0","key":"ref21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888913000118"},{"key":"ref1","article-title":"Autonomic Road Transport Support Systems, ser. Autonomic Systems","author":"mccluskey","year":"2016","journal-title":"Springer Publishing"},{"key":"ref17","article-title":"RHODES: a real-time traffic signal control system: Architecture, algorithms, and analysis","author":"mirchandani","year":"2001","journal-title":"The University of Arizona and Gardner Transportation Systems Tech Rep"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/25.69966"},{"year":"0","key":"ref19","article-title":"PTV VISSIM"},{"journal-title":"Signal Timing Manual","article-title":"Kittelson and Associates","year":"2008","key":"ref18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2004.1336426"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2168260.2168271"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5625145"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)"},{"key":"ref3","article-title":"Reinforcement Learning: An Introduction. Cambridge, Massachusetts: A Bradford Book","author":"suton","year":"1998","journal-title":"The MIT Press"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24580-3_38"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2091408"}],"event":{"name":"2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)","start":{"date-parts":[[2016,11,1]]},"location":"Rio de Janeiro, Brazil","end":{"date-parts":[[2016,11,4]]}},"container-title":["2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7784515\/7795515\/07795890.pdf?arnumber=7795890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T15:27:30Z","timestamp":1682954850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7795890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/itsc.2016.7795890","relation":{},"subject":[],"published":{"date-parts":[[2016,11]]}}}