{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T14:50:27Z","timestamp":1771512627044,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Provincial Key Research and Development Program of Zhejiang","award":["2021C01034"],"award-info":[{"award-number":["2021C01034"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102246"],"award-info":[{"award-number":["62102246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pujiang Program","award":["20PJ1409400"],"award-info":[{"award-number":["20PJ1409400"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,17]]},"DOI":"10.1145\/3511808.3557112","type":"proceedings-article","created":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T01:29:57Z","timestamp":1665883797000},"page":"3545-3554","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["CTRL: Cooperative Traffic Tolling via Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Yiheng","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hexi","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanjie","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mauricio Arango. 2019. Toll Road with Dynamic Congestion Pricing Using Reinforcement Learning. (2019).  Mauricio Arango. 2019. Toll Road with Dynamic Congestion Pricing Using Reinforcement Learning. (2019)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2012.6338724"},{"key":"e_1_3_2_1_3_1","unstructured":"Yu-Han Chang Tracey Ho and Leslie P Kaelbling. 2004. All learning is local: Multi-agent learning in global reward games. (2004).  Yu-Han Chang Tracey Ho and Leslie P Kaelbling. 2004. All learning is local: Multi-agent learning in global reward games. (2004)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11337"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2005.02.018"},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja , Aurick Zhou , Pieter Abbeel , and Sergey Levine . 2018 a. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor . In International conference on machine learning. PMLR , 1861--1870. Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018a. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861--1870."},{"key":"e_1_3_2_1_7_1","unstructured":"Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel etal 2018b. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018).  Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel et al. 2018b. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"Deep reinforcement learning for intelligent transportation systems: A survey","author":"Haydari Ammar","year":"2020","unstructured":"Ammar Haydari and Yasin Yilmaz . 2020. Deep reinforcement learning for intelligent transportation systems: A survey . IEEE Transactions on Intelligent Transportation Systems ( 2020 ). Ammar Haydari and Yasin Yilmaz. 2020. Deep reinforcement learning for intelligent transportation systems: A survey. IEEE Transactions on Intelligent Transportation Systems (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2906260"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2020.9010062"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1177\/0361198105192300107"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep learning. nature","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun , Yoshua Bengio , and Geoffrey Hinton . 2015. Deep learning. nature , Vol. 521 , 7553 ( 2015 ), 436--444. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature, Vol. 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_13_1","unstructured":"Zhenhui Li. n.d. Reinforcement Learning for Traffic Signal Control. https:\/\/traffic-signal-control.github.io  Zhenhui Li. n.d. Reinforcement Learning for Traffic Signal Control. https:\/\/traffic-signal-control.github.io"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2010.03.013"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cstp.2018.06.002"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569737"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569317"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102715"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Wei Qiu Haipeng Chen and Bo An. 2019. Dynamic Electronic Toll Collection via Multi-Agent Deep Reinforcement Learning with Edge-Based Graph Convolutional Networks. In IJCAI. 4568--4574.  Wei Qiu Haipeng Chen and Bo An. 2019. Dynamic Electronic Toll Collection via Multi-Agent Deep Reinforcement Learning with Edge-Based Graph Convolutional Networks. In IJCAI. 4568--4574.","DOI":"10.24963\/ijcai.2019\/635"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2019.12.003"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.08.019"},{"key":"e_1_3_2_1_22_1","volume-title":"Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, et al.","author":"Sunehag Peter","year":"2017","unstructured":"Peter Sunehag , Guy Lever , Audrunas Gruslys , Wojciech Marian Czarnecki , Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, et al. 2017 . Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017). Peter Sunehag, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, et al. 2017. Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"Temporal credit assignment in reinforcement learning. Ph.,D. Dissertation","author":"Sutton Richard Stuart","unstructured":"Richard Stuart Sutton . 1984. Temporal credit assignment in reinforcement learning. Ph.,D. Dissertation . University of Massachusetts Amherst. Richard Stuart Sutton. 1984. Temporal credit assignment in reinforcement learning. Ph.,D. Dissertation. University of Massachusetts Amherst."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"e_1_3_2_1_26_1","volume-title":"A Survey on Traffic Signal Control Methods. arXiv preprint arXiv:1904.08117","author":"Wei Hua","year":"2019","unstructured":"Hua Wei , Guanjie Zheng , Vikash Gayah , and Zhenhui Li. 2019b. A Survey on Traffic Signal Control Methods. arXiv preprint arXiv:1904.08117 ( 2019 ). Hua Wei, Guanjie Zheng, Vikash Gayah, and Zhenhui Li. 2019b. A Survey on Traffic Signal Control Methods. arXiv preprint arXiv:1904.08117 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3141\/1857-10"},{"key":"e_1_3_2_1_28_1","volume-title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario. The World Wide Web Conference (May","author":"Zhang Huichu","year":"2019","unstructured":"Huichu Zhang , Siyuan Feng , Chang Liu , Yaoyao Ding , Yichen Zhu , Zihan Zhou , Weinan Zhang , Yong Yu , Haiming Jin , and Zhenhui Li . 2019 . CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario. The World Wide Web Conference (May 2019). https:\/\/doi.org\/10.1145\/3308558.3314139 10.1145\/3308558.3314139 Huichu Zhang, Siyuan Feng, Chang Liu, Yaoyao Ding, Yichen Zhu, Zihan Zhou, Weinan Zhang, Yong Yu, Haiming Jin, and Zhenhui Li. 2019. CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario. The World Wide Web Conference (May 2019). https:\/\/doi.org\/10.1145\/3308558.3314139"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/18128602.2010.502547"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cities.2019.03.022"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2014.11.009"}],"event":{"name":"CIKM '22: The 31st ACM International Conference on Information and Knowledge Management","location":"Atlanta GA USA","acronym":"CIKM '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 31st ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557112","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3511808.3557112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:56Z","timestamp":1750188656000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,17]]},"references-count":31,"alternative-id":["10.1145\/3511808.3557112","10.1145\/3511808"],"URL":"https:\/\/doi.org\/10.1145\/3511808.3557112","relation":{},"subject":[],"published":{"date-parts":[[2022,10,17]]},"assertion":[{"value":"2022-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}