{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T04:22:52Z","timestamp":1785644572405,"version":"3.56.0"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["JP21K12024"],"award-info":[{"award-number":["JP21K12024"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3225431","type":"journal-article","created":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T19:37:30Z","timestamp":1669664250000},"page":"128943-128950","source":"Crossref","is-referenced-by-count":41,"title":["Traffic Signal Control System Using Deep Reinforcement Learning With Emphasis on Reinforcing Successful Experiences"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3412-8558","authenticated-orcid":false,"given":"Naoki","family":"Kodama","sequence":"first","affiliation":[{"name":"Department of Computer Science, School of Science and Technology, Meiji University, Tama-ku, Kawasaki, Kanagawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5410-7514","authenticated-orcid":false,"given":"Taku","family":"Harada","sequence":"additional","affiliation":[{"name":"Department of Industrial Administration, Faculty of Science and Technology, Tokyo University of Science, Noda-shi, Chiba, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8175-213X","authenticated-orcid":false,"given":"Kazuteru","family":"Miyazaki","sequence":"additional","affiliation":[{"name":"National Institution for Academic Degrees and Quality Enhancement of Higher Education, Kodaira-shi, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6958095"},{"key":"ref11","first-page":"218","article-title":"Multiagent coordination with learning classifier systems","author":"sen","year":"1995","journal-title":"Adaption and Learning in Multi-Agent Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851690"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3126365"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.9746\/jcmsi.11.207"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref16","article-title":"Adaptive traffic signal control: Deep reinforcement learning algorithm with experience replay and target network","author":"gao","year":"2017","journal-title":"arXiv 1705 02755"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref18","article-title":"RLlib: Abstractions for distributed reinforcement learning","author":"liang","year":"2017","journal-title":"arXiv 1712 09381"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref3","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":"ref6","article-title":"Using a deep reinforcement learning agent for traffic signal control","author":"genders","year":"2016","journal-title":"arXiv 1611 01142"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2091408"},{"key":"ref8","article-title":"Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization","author":"zhang","year":"2019","journal-title":"arXiv 1909 10651"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2997896"},{"key":"ref2","year":"2012","journal-title":"Ministry of Health Labour and Welfare Basic Survey on Wage Structure"},{"key":"ref1","year":"0","journal-title":"Ministry of Land Infrastructure Transport and Tourism Ministry of Land Infrastructure Transport and Tourism Productivity Revolution Project"},{"key":"ref9","first-page":"1151","article-title":"Multi-agent reinforcement learning for traffic signal control","author":"marco","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09965397.pdf?arnumber=9965397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T21:24:16Z","timestamp":1673299456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9965397\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3225431","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}