{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T05:41:33Z","timestamp":1760852493218,"version":"build-2065373602"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"31","license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Natural Science Foundation","award":["CPS-173996"],"award-info":[{"award-number":["CPS-173996"]}]},{"DOI":"10.13039\/501100010229","name":"Natural Science Foundation of Tianjin Municipal Science and Technology Commission","doi-asserted-by":"publisher","award":["IIS-1724157"],"award-info":[{"award-number":["IIS-1724157"]}],"id":[{"id":"10.13039\/501100010229","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation","award":["FAIN-2019844"],"award-info":[{"award-number":["FAIN-2019844"]}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-18-2243"],"award-info":[{"award-number":["N00014-18-2243"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-19-2-0333"],"award-info":[{"award-number":["W911NF-19-2-0333"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s00521-023-09183-8","type":"journal-article","created":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T11:02:15Z","timestamp":1700996535000},"page":"25695-25708","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning a robust multiagent driving policy for traffic congestion reduction"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5098-7075","authenticated-orcid":false,"given":"Yulin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Macke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxun","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sharon","family":"Hornstein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Urieli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"unstructured":"Lomax T, Schrank D, Eisele B (2021) Urban mobility report. https:\/\/mobility.tamu.edu\/umr\/. Accessed: 2021-10-07","key":"9183_CR1"},{"issue":"3","key":"9183_CR2","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/10\/3\/033001","volume":"10","author":"Y Sugiyama","year":"2008","unstructured":"Sugiyama Y, Fukui M, Kikuchi M, Hasebe K, Nakayama A, Nishinari K, Tadaki S-I, Yukawa S (2008) Traffic jams without bottlenecks\u2014experimental evidence for the physical mechanism of the formation of a jam. New J Phys 10(3):033001","journal-title":"New J Phys"},{"key":"9183_CR3","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/j.trc.2018.02.005","volume":"89","author":"RE Stern","year":"2018","unstructured":"Stern RE, Cui S, Delle Monache ML, Bhadani R, Bunting M, Churchill M, Hamilton N, Pohlmann H, Wu F, Piccoli B (2018) Dissipation of stop-and-go waves via control of autonomous vehicles: Field experiments. Transp Res Part C Emerg Technol 89:205\u2013221","journal-title":"Transp Res Part C Emerg Technol"},{"issue":"11","key":"9183_CR4","doi-asserted-by":"publisher","first-page":"3752","DOI":"10.1143\/JPSJ.69.3752","volume":"69","author":"N Mitarai","year":"2000","unstructured":"Mitarai N, Nakanishi H (2000) Convective instability and structure formation in traffic flow. J Phys Soc Jpn 69(11):3752\u20133761","journal-title":"J Phys Soc Jpn"},{"key":"9183_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102954","volume":"123","author":"L Cummins","year":"2021","unstructured":"Cummins L, Sun Y, Reynolds M (2021) Simulating the effectiveness of wave dissipation by followerstopper autonomous vehicles. Transp Res Part C Emerg Technol 123:102954","journal-title":"Transp Res Part C Emerg Technol"},{"key":"9183_CR6","volume-title":"Stuck in traffic: coping with peak-hour traffic congestion","author":"A Downs","year":"2000","unstructured":"Downs A (2000) Stuck in traffic: coping with peak-hour traffic congestion. Brookings Institution Press, JSTOR"},{"key":"9183_CR7","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT press, Cambridge, MA"},{"unstructured":"Wu C, Kreidieh A, Vinitsky E, Bayen AM (2017) Emergent behaviors in mixed-autonomy traffic. In: Conference on robot learning, pp. 398\u2013407","key":"9183_CR8"},{"doi-asserted-by":"crossref","unstructured":"Kreidieh AR, Wu C, Bayen AM (2018) Dissipating stop-and-go waves in closed and open networks via deep reinforcement learning. In: 2018 21st international conference on intelligent transportation systems (ITSC), pp. 1475\u20131480","key":"9183_CR9","DOI":"10.1109\/ITSC.2018.8569485"},{"doi-asserted-by":"crossref","unstructured":"Vinitsky E, Parvate K, Kreidieh A, Wu C, Bayen A (2018) Lagrangian control through deep-rl: Applications to bottleneck decongestion. In: 21st International conference on intelligent transportation systems (ITSC), pp 759\u2013765","key":"9183_CR10","DOI":"10.1109\/ITSC.2018.8569615"},{"key":"9183_CR11","first-page":"174","volume":"23","author":"M Treiber","year":"2017","unstructured":"Treiber M, Kesting A (2017) The intelligent driver model with stochasticity-new insights into traffic flow oscillations. Transp Res Proc 23:174\u2013187","journal-title":"Transp Res Proc"},{"unstructured":"Cui J, Macke W, Yedidsion H, Goyal A, Urieli D, Stone P (2021) Scalable multiagent driving policies for reducing traffic congestion. In: Proceedings of the 20th international conference on autonomous agents and multi agent systems, pp. 386\u2013394","key":"9183_CR12"},{"unstructured":"Pinto L, Davidson J, Sukthankar R, Gupta A (2017) Robust adversarial reinforcement learning. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th international conference on machine learning, vol 70, pp 2817\u20132826","key":"9183_CR13"},{"doi-asserted-by":"crossref","unstructured":"Tobin J, Fong R, Ray A, Schneider J, Zaremba W, Abbeel P (2017) Domain randomization for transferring deep neural networks from simulation to the real world. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS). pp. 23\u201330. IEEE","key":"9183_CR14","DOI":"10.1109\/IROS.2017.8202133"},{"key":"9183_CR15","first-page":"1","volume":"12","author":"C Wu","year":"2021","unstructured":"Wu C, Kreidieh AR, Parvate K, Vinitsky E, Bayen AM (2021) Flow: a modular learning framework for mixed autonomy traffic. IEEE Trans Robot 12:1\u201317","journal-title":"IEEE Trans Robot"},{"unstructured":"Parvate K (2020) On training robust policies for flow smoothing (UCB\/EECS-2020-197)","key":"9183_CR16"},{"key":"9183_CR17","first-page":"25689","volume":"51","author":"E Vinitsky","year":"2023","unstructured":"Vinitsky E, Lichtle N, Parvate K, Bayen A (2023) Optimizing mixed autonomy traffic flow with decentralized autonomous vehicles and multi-agent RL. ACM Trans Cyber Phys Syst 51:25689","journal-title":"ACM Trans Cyber Phys Syst"},{"issue":"4","key":"9183_CR18","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/0191-2615(94)90002-7","volume":"28","author":"CF Daganzo","year":"1994","unstructured":"Daganzo CF (1994) The cell transmission model: A dynamic representation of highway traffic consistent with the hydrodynamic theory. Transp Res Part B Methodol 28(4):269\u2013287","journal-title":"Transp Res Part B Methodol"},{"issue":"2","key":"9183_CR19","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1109\/TASE.2022.3168621","volume":"20","author":"Z Yan","year":"2023","unstructured":"Yan Z, Kreidieh AR, Vinitsky E, Bayen AM, Wu C (2023) Unified automatic control of vehicular systems with reinforcement learning. IEEE Trans Autom Sci Eng 20(2):789\u2013804","journal-title":"IEEE Trans Autom Sci Eng"},{"issue":"4","key":"9183_CR20","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein DS, Givan R, Immerman N, Zilberstein S (2002) The complexity of decentralized control of markov decision processes. Math Oper Res 27(4):819\u2013840","journal-title":"Math Oper Res"},{"issue":"3 &4","key":"9183_CR21","first-page":"45665253","volume":"5","author":"D Krajzewicz","year":"2012","unstructured":"Krajzewicz D, Erdmann J, Behrisch M, Bieker L (2012) Recent development and applications of sumo-simulation of urban mobility. Int J Adv Syst Meas 5(3 &4):45665253","journal-title":"Int J Adv Syst Meas"},{"unstructured":"Krau\u00df S (1998) Microscopic modeling of traffic flow: Investigation of collision free vehicle dynamics. Technical report DLR-FB-98-08, German center for air and space navigation","key":"9183_CR22"},{"unstructured":"Duan Y, Chen X, Houthooft R, Schulman J, Abbeel P (2016) Benchmarking deep reinforcement learning for continuous control. In: International conference on machine learning, pp 1329\u20131338","key":"9183_CR23"},{"unstructured":"Wu C, Kreidieh A, Parvate K, Vinitsky E, Bayen AM (2017) Flow: Architecture and benchmarking for reinforcement learning in traffic control. arXiv preprint arXiv:1710.05465","key":"9183_CR24"},{"unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","key":"9183_CR25"},{"issue":"9","key":"9183_CR26","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1016\/j.trb.2008.02.002","volume":"42","author":"N Geroliminis","year":"2008","unstructured":"Geroliminis N, Daganzo CF (2008) Existence of urban-scale macroscopic fundamental diagrams: some experimental findings. Transp Res Part B Methodol 42(9):759\u2013770","journal-title":"Transp Res Part B Methodol"},{"unstructured":"Boyles SD, Lownes NE, Unnikrishnan A (2022) Transportation network analysis vol 1. 0.90 ed","key":"9183_CR27"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09183-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-09183-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09183-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T05:02:22Z","timestamp":1760850142000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-09183-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"references-count":27,"journal-issue":{"issue":"31","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["9183"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-09183-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"18 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The prior and current affiliations that are in the conflict of interest include the University of\u00a0Texas at Austin, General Motors, Texas A&M University, and Amazon Robotics. The corresponding author is prepared to collect documentation of compliance with ethical standards and send if requested.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}