{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T01:47:18Z","timestamp":1769824038528,"version":"3.49.0"},"reference-count":50,"publisher":"Informa UK Limited","issue":"4","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent Transportation Systems"],"published-print":{"date-parts":[[2022,7,4]]},"DOI":"10.1080\/15472450.2021.1934679","type":"journal-article","created":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T04:03:53Z","timestamp":1623038633000},"page":"476-485","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":10,"title":["A cold-start-free reinforcement learning approach for traffic signal control"],"prefix":"10.1080","volume":"26","author":[{"given":"Nan","family":"Xiao","sequence":"first","affiliation":[{"name":"Alibaba Cloud Intelligence, Alibaba Group, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinqiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuehu","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Intelligence, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2021,6,6]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.06.003"},{"key":"CIT0002","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"CIT0003","unstructured":"Baker, B., Gupta, O., Naik, N. & Raskar, R. (2016). Designing neural network architectures using reinforcement learning. arXiv preprint (arXiv:1611.02167)."},{"key":"CIT0004","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.286"},{"key":"CIT0005","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5113-5_3"},{"key":"CIT0006","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2015.01.007"},{"key":"CIT0007","unstructured":"Fortunato, M., Azar, M. G., Piot, B., Menick, J., Osband, I., Graves, A., Mnih, V., Munos, R., Hassabis, D., Pietquin, O., Blundell, C. & Legg, S. (2017). Noisy networks for exploration. arXiv preprint (arXiv:1706.10295)."},{"key":"CIT0008","unstructured":"Gao, J., Shen, Y., Liu, J., Ito, M. & Shiratori, N. (2017). Adaptive traffic signal control: Deep reinforcement learning algorithm with experience replay and target network. arXiv preprint (arXiv:1705.02755)."},{"key":"CIT0009","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2018.1491003"},{"key":"CIT0010","volume-title":"Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow","author":"G\u00e9ron A.","year":"2019"},{"key":"CIT0011","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"CIT0012","unstructured":"Hansen, S. (2016). Using deep Q-learning to control optimization hyperparameters. arXiv preprint (arXiv:1602.04062)."},{"key":"CIT0013","first-page":"2094","author":"Hasselt H. V.","year":"2016","journal-title":"Proceedings of 30th AAAI conference on artificial intelligence"},{"key":"CIT0014","volume-title":"2015 AAAI Fall Symposium Series","author":"Hausknecht M.","year":"2015"},{"key":"CIT0015","volume-title":"Proceedings of 32nd AAAI conference on artificial intelligence","author":"Hessel M.","year":"2018"},{"key":"CIT0016","volume-title":"Proceedings of 32nd AAAI conference on artificial intelligence","author":"Hester T.","year":"2018"},{"key":"CIT0017","unstructured":"Highway Capacity Manual (2000). National Academy of Sciences."},{"key":"CIT0018","volume-title":"Deep reinforcement learning hands-on.","author":"Lapan M.","year":"2018"},{"key":"CIT0019","unstructured":"Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D. & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint (arXiv:1509.02971)."},{"key":"CIT0020","volume-title":"Optimal timing settings and detector lengths of presence mode full-actuated control","author":"Lin F.-B.","year":"1985"},{"key":"CIT0021","first-page":"40","author":"Little J. D. C.","year":"1981","journal-title":"Transportation Research Record"},{"key":"CIT0022","doi-asserted-by":"publisher","DOI":"10.1080\/1023697X.1999.10667806"},{"key":"CIT0023","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"CIT0024","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(00)00047-4"},{"key":"CIT0025","first-page":"1928","author":"Mnih V.","year":"2016","journal-title":"International conference on machine learning"},{"key":"CIT0026","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D. & Riedmiller, M. (2013). Playing atari with deep reinforcement learning. arXiv preprint. (arXiv:1312.5602)"},{"key":"CIT0027","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2017.0153"},{"key":"CIT0028","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.819610"},{"key":"CIT0029","first-page":"5690","author":"Racani\u00e8re S.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0030","volume-title":"Traffic engineering","author":"Roess R. P.","year":"2019","edition":"5"},{"key":"CIT0031","first-page":"627","volume-title":"Proceedings of 14th International Conference on Artificial Intelligence and Statistics","author":"Ross S.","year":"2011"},{"key":"CIT0032","first-page":"110","volume-title":"Proceedings of the Workshops of International Conference on Machine Learning","author":"Satija H.","year":"2016"},{"key":"CIT0033","unstructured":"Schaul, T., Quan, J., Antonoglou, I. & Silver, D. (2015). Prioritized experience replay. arXiv preprint (arXiv:1511.05952)."},{"key":"CIT0034","first-page":"1889","volume-title":"International Conference on Machine Learning","author":"Schulman J.","year":"2015"},{"key":"CIT0035","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"CIT0036","doi-asserted-by":"publisher","DOI":"10.17226\/14364"},{"key":"CIT0037","volume-title":"Reinforcement learning: an introduction","author":"Sutton R. S.","year":"2018"},{"key":"CIT0038","doi-asserted-by":"publisher","DOI":"10.17226\/22097"},{"key":"CIT0039","volume-title":"Proceedings of Learning, Inference and Control of Multi-Agent Systems","author":"Van der Pol E.","year":"2016"},{"key":"CIT0040","unstructured":"Ve\u010der\u00edk, M., Hester, T., Scholz, J., Wang, F., Pietquin, O., Piot, B. \u2026 Riedmiller, M. (2018). Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards. arXiv preprint (arXiv:1707.08817)."},{"key":"CIT0041","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2018.5170"},{"key":"CIT0042","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2016.2634459"},{"key":"CIT0043","first-page":"1995","volume-title":"International Conference on Machine Learning","author":"Wang Z.","year":"2016"},{"key":"CIT0044","unstructured":"Webster, F. V. (1958). Traffic signal settings. Department of Scientific and Industrial Research Road Research Laboratory, Technical Report."},{"key":"CIT0045","unstructured":"Wei, H., Zheng, G., Gayah, V. & Li, Z. (2020). A survey on traffic signal control methods. arXiv preprint (arXiv:1904.08117)."},{"key":"CIT0046","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"CIT0047","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7402528"},{"key":"CIT0048","first-page":"2837","volume-title":"Proceedings of 29th ACM International Conference on Information and Knowledge Management","author":"Xiao N.","year":"2020"},{"key":"CIT0049","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"},{"key":"CIT0050","unstructured":"Zhang, X. & Ma, H. (2018). Pretraining deep actor-critic reinforcement learning algorithms with expert demonstrations. arXiv preprint (arXiv:1801.10459)."}],"container-title":["Journal of Intelligent Transportation Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/15472450.2021.1934679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T05:49:36Z","timestamp":1655358576000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/15472450.2021.1934679"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,7,4]]}},"alternative-id":["10.1080\/15472450.2021.1934679"],"URL":"https:\/\/doi.org\/10.1080\/15472450.2021.1934679","relation":{},"ISSN":["1547-2450","1547-2442"],"issn-type":[{"value":"1547-2450","type":"print"},{"value":"1547-2442","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,6]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=gits20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=gits20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2019-12-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-17","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}