{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:07:19Z","timestamp":1774051639172,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Canada Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,19]]},"DOI":"10.1109\/itsc48978.2021.9564528","type":"proceedings-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T19:52:26Z","timestamp":1635191546000},"page":"2525-2532","source":"Crossref","is-referenced-by-count":6,"title":["Microscopic Model-Based RL Approaches for Traffic Signal Control Generalize Better than Model-Free RL Approaches"],"prefix":"10.1109","author":[{"given":"Parth","family":"Jaggi","sequence":"first","affiliation":[]},{"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Nicolas","family":"Carrara","sequence":"additional","affiliation":[]},{"given":"Scott","family":"Sanner","sequence":"additional","affiliation":[]},{"given":"Baher","family":"Abdulhai","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2012.02.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.05.011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294171"},{"key":"ref34","article-title":"A non-homogenous time mixed integer lp formulation for traffic signal control","volume":"2525","author":"guilliard","year":"2016","journal-title":"Transportation Research Record Journal of the Transportation Research Board"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888900007724"},{"key":"ref11","first-page":"1068","article-title":"On-line policy improvement using monte-carlo search","volume":"9","author":"tesauro","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref14","first-page":"72","article-title":"Efficient selectivity and backup operators in monte-carlo tree search","author":"coulom","year":"2006","journal-title":"International conference on computers and games"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3328\/TL.2010.02.02.89-110"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/34.44404"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11028","article-title":"An analysis of monte carlo tree search","volume":"31","author":"james","year":"2017","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref28","author":"oroojlooy","year":"2020","journal-title":"Attendlight Universal attention-based reinforcement learning model for traffic signal control"},{"key":"ref4","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref3","article-title":"Scat the sydney coordinated adaptive traffic system: philosophy and benefits","volume":"2","author":"sims","year":"1979","journal-title":"International Symposium on Traffic Control Systems 1979"},{"key":"ref6","author":"gao","year":"2017","journal-title":"Adaptive Traffic Signal Control Deep Reinforcement Learning Algorithm with Experience Replay and Target Network"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref5","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917493"},{"key":"ref2","author":"hunt","year":"1981","journal-title":"SCOOT-a traffic responsive method of coordinating signals"},{"key":"ref1","volume":"1","year":"1994","journal-title":"Engineering and Medicine Curbing Gridlock Peak-Period Fees to Relieve Traffic Congestion–Special Report 242"},{"key":"ref9","author":"zhang","year":"2017","journal-title":"Understanding deep learning requires rethinking generalization"},{"key":"ref20","article-title":"Deep reinforcement learning with double q-learning","volume":"abs 1509 6461","author":"van hasselt","year":"2015","journal-title":"CoRR"},{"key":"ref22","article-title":"Ray rllib: A composable and scalable reinforcement learning library","volume":"abs 1712 9381","author":"liang","year":"2017","journal-title":"CoRR"},{"key":"ref21","author":"horgan","year":"2018","journal-title":"Distributed prioritized experience replay"},{"key":"ref24","author":"machado","year":"2017","journal-title":"Revisiting the arcade learning environment Evaluation protocols and open problems for general agents"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref26","article-title":"Cooperative deep reinforcement learning for large-scale traffic grid signal control","author":"tan","year":"2019","journal-title":"IEEE Transactions on Cybernetics"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"}],"event":{"name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","location":"Indianapolis, IN, USA","start":{"date-parts":[[2021,9,19]]},"end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Intelligent Transportation Systems Conference (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9564393\/9564395\/09564528.pdf?arnumber=9564528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T20:12:30Z","timestamp":1673640750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/itsc48978.2021.9564528","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}