{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:41:17Z","timestamp":1777128077887,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/ccta41146.2020.9206275","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:39:12Z","timestamp":1601426352000},"page":"358-365","source":"Crossref","is-referenced-by-count":13,"title":["Multi-Agent Bootstrapped Deep Q-Network for Large-Scale Traffic Signal Control"],"prefix":"10.1109","author":[{"given":"Tian","family":"Tan","sequence":"first","affiliation":[]},{"given":"Tianshu","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref31","article-title":"Behaviour suite for reinforcement learning","author":"osband","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref10","article-title":"Coordinated deep reinforcement learners for traffic light control","author":"van","year":"0","journal-title":"Proceedings of Learning Inference and Control of Multi-Agent Systems (at NIPS 2016)"},{"key":"ref11","article-title":"Multi-agent deep reinforcement learning for large-scale traffic signal control","author":"chu","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref13","first-page":"8617","article-title":"Randomized prior functions for deep reinforcement learning","author":"osband","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7525014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.103415"},{"key":"ref17","article-title":"Recent development and applications of sumo-simulation of urban mobility","volume":"5","author":"krajzewicz","year":"2012","journal-title":"International Journal on Advances in Systems and Measurements"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref19","author":"wiering","year":"2004","journal-title":"Intelligent traffic light control"},{"key":"ref28","author":"tan","year":"2019","journal-title":"Parameterized indexed value function for efficient exploration in reinforcement learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"},{"key":"ref27","author":"osband","year":"2014","journal-title":"Generalization and exploration via randomized value functions"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2009.653"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21608\/mjeer.2020.68928"},{"key":"ref29","first-page":"66","article-title":"Cooperative multiagent control using deep reinforcement learning","author":"gupta","year":"0","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916776"},{"key":"ref8","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0191-2615(03)00015-8"},{"key":"ref9","author":"li","year":"2017","journal-title":"Paraphrase generation with deep reinforcement learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2050688"},{"key":"ref20","first-page":"412","article-title":"Reinforcement learning with function approximation for traffic signal control","volume":"12","author":"prashanth","year":"2010","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56994-9_44"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7172018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"ref23","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref25","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2020 IEEE Conference on Control Technology and Applications (CCTA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2020,8,24]]},"end":{"date-parts":[[2020,8,26]]}},"container-title":["2020 IEEE Conference on Control Technology and Applications (CCTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200884\/9206152\/09206275.pdf?arnumber=9206275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:36:02Z","timestamp":1656344162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ccta41146.2020.9206275","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}