{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:33:07Z","timestamp":1783438387328,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,19]],"date-time":"2020-10-19T00:00:00Z","timestamp":1603065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,19]]},"DOI":"10.1145\/3340531.3411871","type":"proceedings-article","created":{"date-parts":[[2020,10,19]],"date-time":"2020-10-19T06:18:51Z","timestamp":1603088331000},"page":"805-814","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Cooperative Multi-Agent Reinforcement Learning in Express System"],"prefix":"10.1145","author":[{"given":"Yexin","family":"Li","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zheng","sequence":"additional","affiliation":[{"name":"JD Intelligent Cities Research & JD Intelligent Cities Business Unit, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,19]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"L. Busoniu R. Babuska and D. B. Schutter. 2010. Multi-Agent Reinforcement Learning: An Overview. Springer.  L. Busoniu R. Babuska and D. B. Schutter. 2010. Multi-Agent Reinforcement Learning: An Overview. Springer.","DOI":"10.1109\/ADPRL.2011.5967353"},{"key":"e_1_3_2_2_2_1","volume-title":"Crowddeliver: Planning City-Wide Package Delivery Paths Leveraging the Crowd of Taxis","author":"Chen C.","year":"2017","unstructured":"C. Chen , D. Zhang , X. Ma , B. Guo , L. Wang , Y. Wang , and E. Sha . 2017 . Crowddeliver: Planning City-Wide Package Delivery Paths Leveraging the Crowd of Taxis . IEEE Trans. Intelligent Transportation Systems ( 2017). C. Chen, D. Zhang, X. Ma, B. Guo, L. Wang, Y. Wang, and E. Sha. 2017. Crowddeliver: Planning City-Wide Package Delivery Paths Leveraging the Crowd of Taxis. IEEE Trans. Intelligent Transportation Systems (2017)."},{"key":"e_1_3_2_2_3_1","volume-title":"Proc. SIGKDD.","author":"Chen S.","unstructured":"S. Chen , Y. Yu , Q. Da , J. Tan , H. Huang , and H. Tang . 2018. Stabilizing Reinforcement Learning in Dynamic Environment with Application to Online Recommendation . In Proc. SIGKDD. S. Chen, Y. Yu, Q. Da, J. Tan, H. Huang, and H. Tang. 2018. Stabilizing Reinforcement Learning in Dynamic Environment with Application to Online Recommendation. In Proc. SIGKDD."},{"key":"e_1_3_2_2_4_1","unstructured":"N. J. Foerster M. Y. Assael D. N. Freitas and S. Whiteson. 2016. Learning to Communicate to Solve Riddles with Deep Distribute Recurrent Q-Networks. In arXiv.  N. J. Foerster M. Y. Assael D. N. Freitas and S. Whiteson. 2016. Learning to Communicate to Solve Riddles with Deep Distribute Recurrent Q-Networks. In arXiv."},{"key":"e_1_3_2_2_5_1","volume-title":"Proc. IJCAI.","author":"Ghosh S.","unstructured":"S. Ghosh , M. Trick , and P. Varakantham . 2016. Robust Reposition to Counter Unpredictable Demand in Bike Sharing Systems . In Proc. IJCAI. S. Ghosh, M. Trick, and P. Varakantham. 2016. Robust Reposition to Counter Unpredictable Demand in Bike Sharing Systems. In Proc. IJCAI."},{"key":"e_1_3_2_2_6_1","unstructured":"I. Goodfellow Y. Bengio and A. Courville. 2016. Deep Learning. MIT.  I. Goodfellow Y. Bengio and A. Courville. 2016. Deep Learning. MIT."},{"key":"e_1_3_2_2_7_1","volume-title":"Proc. SIGKDD.","author":"Hu Y.","unstructured":"Y. Hu , Q. Da , A. Zeng , Y. Yu , and Y. Xu . 2018. Reinforcement Learning to Rank in E-commerce Search Engine: Formalization, Analysis, and Application . In Proc. SIGKDD. Y. Hu, Q. Da, A. Zeng, Y. Yu, and Y. Xu. 2018. Reinforcement Learning to Rank in E-commerce Search Engine: Formalization, Analysis, and Application. In Proc. SIGKDD."},{"key":"e_1_3_2_2_8_1","volume-title":"Proc. SIGKDD.","author":"Hulot P.","unstructured":"P. Hulot , D. Aloise , and S. D. Jena . 2018. Towards Station-Level Demand Prediction for Effective Rebalancing in Bike-Sharing Systems . In Proc. SIGKDD. P. Hulot, D. Aloise, and S. D. Jena. 2018. Towards Station-Level Demand Prediction for Effective Rebalancing in Bike-Sharing Systems. In Proc. SIGKDD."},{"key":"e_1_3_2_2_9_1","volume-title":"Proc. ICML.","author":"Kok R. J.","unstructured":"R. J. Kok and N. Vlassis . 2004. Sparse Cooperative Q-Learning . In Proc. ICML. R. J. Kok and N. Vlassis. 2004. Sparse Cooperative Q-Learning. In Proc. ICML."},{"key":"e_1_3_2_2_10_1","volume-title":"Proc. AAMAS.","author":"Lee H.","unstructured":"H. Lee and T. Lee . 2019. Improve Cooperative Multi-Agent Reinforcement Learning Algorithm Augmented by Mixing Demonstrations from Centralized Policy . In Proc. AAMAS. H. Lee and T. Lee. 2019. Improve Cooperative Multi-Agent Reinforcement Learning Algorithm Augmented by Mixing Demonstrations from Centralized Policy. In Proc. AAMAS."},{"key":"e_1_3_2_2_11_1","volume-title":"Proc. SIGKDD.","author":"Li T.","unstructured":"T. Li , J. Zhang , K. Bao , Y. Liang , Y. Li , and Y. Zheng . 2020. AutoST: Eicient Neural Architecture Search for Spatio-Temporal Prediction . In Proc. SIGKDD. T. Li, J. Zhang, K. Bao, Y. Liang, Y. Li, and Y. Zheng. 2020. AutoST: Eicient Neural Architecture Search for Spatio-Temporal Prediction. In Proc. SIGKDD."},{"key":"e_1_3_2_2_12_1","volume-title":"Proc. AAMAS.","author":"Li X.","unstructured":"X. Li , J. Zhang , J. Bian , Y. Tong , and T. Liu . 2019. A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics Network . In Proc. AAMAS. X. Li, J. Zhang, J. Bian, Y. Tong, and T. Liu. 2019. A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics Network. In Proc. AAMAS."},{"key":"e_1_3_2_2_13_1","unstructured":"Y. Li and Y. Zheng. 2019. Citywide Bike Usage Prediction in a Bike-Sharing System. Transaction on Knowledge and Data Engineering (2019).  Y. Li and Y. Zheng. 2019. Citywide Bike Usage Prediction in a Bike-Sharing System. Transaction on Knowledge and Data Engineering (2019)."},{"key":"e_1_3_2_2_14_1","volume-title":"Proc. SIGKDD.","author":"Li Y.","unstructured":"Y. Li , Y. Zheng , and Q. Yang . 2018. Dynamic Bike Reposition: A Spatio-Temporal Reinforcement Learning Approach . In Proc. SIGKDD. Y. Li, Y. Zheng, and Q. Yang. 2018. Dynamic Bike Reposition: A Spatio-Temporal Reinforcement Learning Approach. In Proc. SIGKDD."},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. SIGKDD.","author":"Li Y.","unstructured":"Y. Li , Y. Zheng , and Q. Yang . 2019. Efficient and Effective Express via Contextual Cooperative Reinforcement Learning . In Proc. SIGKDD. Y. Li, Y. Zheng, and Q. Yang. 2019. Efficient and Effective Express via Contextual Cooperative Reinforcement Learning. In Proc. SIGKDD."},{"key":"e_1_3_2_2_16_1","volume-title":"Proc. SIGSPATIAL.","author":"Li Y.","unstructured":"Y. Li , Y. Zheng , H. Zhang , and L. Chen . 2015. Traffic Prediction in a Bike-Sharing System . In Proc. SIGSPATIAL. Y. Li, Y. Zheng, H. Zhang, and L. Chen. 2015. Traffic Prediction in a Bike-Sharing System. In Proc. SIGSPATIAL."},{"key":"e_1_3_2_2_17_1","volume-title":"Proc. IJCAI.","author":"Liang Y.","unstructured":"Y. Liang , S. Ke , J. Zhang , X. Yi , and Y. Zheng . 2018. GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction . In Proc. IJCAI. Y. Liang, S. Ke, J. Zhang, X. Yi, and Y. Zheng. 2018. GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction. In Proc. IJCAI."},{"key":"e_1_3_2_2_18_1","volume":"201","author":"Lin K.","unstructured":"K. Lin , R. Zhao , Z. Xu , and J. Zhou. 201 8. Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning. In Proc. SIGKDD. K. Lin, R. Zhao, Z. Xu, and J. Zhou. 2018. Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning. In Proc. SIGKDD.","journal-title":"J. Zhou."},{"key":"e_1_3_2_2_19_1","volume-title":"Proc. SIGKDD.","author":"Liu J.","unstructured":"J. Liu , L. Sun , W. Chen , and H. Xiong . 2016. Rebalancing Bike Sharing Systems: A Multi-Source Data Smart Optimization . In Proc. SIGKDD. J. Liu, L. Sun, W. Chen, and H. Xiong. 2016. Rebalancing Bike Sharing Systems: A Multi-Source Data Smart Optimization. In Proc. SIGKDD."},{"key":"e_1_3_2_2_20_1","volume-title":"Proc. NIPS.","author":"Lowe R.","unstructured":"R. Lowe , Y. Wu , A. Tamar , J. Harb , P. Abbeel , and I. Mordatch . 2017. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments . In Proc. NIPS. R. Lowe, Y. Wu, A. Tamar, J. Harb, P. Abbeel, and I. Mordatch. 2017. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. In Proc. NIPS."},{"key":"e_1_3_2_2_21_1","volume-title":"Proc. Orange D4D Challenge.","author":"Mclnerney J.","unstructured":"J. Mclnerney , A. Rogers , and N. R. Jennings . 2014. Crowdsourcing Physical Package Delivery Using the Existing Routine Mobility of A Local Population . In Proc. Orange D4D Challenge. J. Mclnerney, A. Rogers, and N. R. Jennings. 2014. Crowdsourcing Physical Package Delivery Using the Existing Routine Mobility of A Local Population. In Proc. Orange D4D Challenge."},{"key":"e_1_3_2_2_22_1","unstructured":"V. Mnih K. Kavukcuoglu D. Silver A. Graves I. Antonoglou D. Wierstra and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. In arXiv.  V. Mnih K. Kavukcuoglu D. Silver A. Graves I. Antonoglou D. Wierstra and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. In arXiv."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"V. Mnih K. Kavukcuoglu D. Silver A. A. Rusu J. Veness M. G. Bellemare A. Graves M. Riedmiller A. K. Fidjeland G. Ostrovski S. Petersen C. Beattie A. Sadik I. Antonoglou H. King D. Kumaran D. Wierstra S. Legg and D. Hassabis. 2015. Human-Level Control through Deep Reinforcement Learning. Nature (2015).  V. Mnih K. Kavukcuoglu D. Silver A. A. Rusu J. Veness M. G. Bellemare A. Graves M. Riedmiller A. K. Fidjeland G. Ostrovski S. Petersen C. Beattie A. Sadik I. Antonoglou H. King D. Kumaran D. Wierstra S. Legg and D. Hassabis. 2015. Human-Level Control through Deep Reinforcement Learning. Nature (2015).","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_2_24_1","volume-title":"Proc. ICWSM.","author":"Sadilek A.","unstructured":"A. Sadilek , J. Krumm , and E. Horvitz . 2013. Crowdphysics: Planned and Opportunistic Crowdsourcing for Physical Tasks . In Proc. ICWSM. A. Sadilek, J. Krumm, and E. Horvitz. 2013. Crowdphysics: Planned and Opportunistic Crowdsourcing for Physical Tasks. In Proc. ICWSM."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"D. Silver A. Huang J. C. Maddison A. Guez L. Sifre G. Driessche J. Schrittwieser I. Antonoglou V. Panneershelvam M. Lanctot S. Dieleman D. Grewe J. Nham N. Kalchbrenner I. Sutskever T. Lillicrap M. Leach K. Kavukcuoglu T. Graepel and D. Hassabis. 2016. Mastering the Game of Go with Deep Neural Network and Tree Search. Nature (2016).  D. Silver A. Huang J. C. Maddison A. Guez L. Sifre G. Driessche J. Schrittwieser I. Antonoglou V. Panneershelvam M. Lanctot S. Dieleman D. Grewe J. Nham N. Kalchbrenner I. Sutskever T. Lillicrap M. Leach K. Kavukcuoglu T. Graepel and D. Hassabis. 2016. Mastering the Game of Go with Deep Neural Network and Tree Search. Nature (2016).","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_2_27_1","unstructured":"A. Tampuu T. Matiisen D. Kodelja I. Kuzovkin K. Korjus J. Aru and R. Vincent. 2015. Multiagent Cooperation and Competition with Deep Reinforcement Learning. In arXiv.  A. Tampuu T. Matiisen D. Kodelja I. Kuzovkin K. Korjus J. Aru and R. Vincent. 2015. Multiagent Cooperation and Competition with Deep Reinforcement Learning. In arXiv."},{"key":"e_1_3_2_2_28_1","volume-title":"Proc. AAAI.","author":"Wang D.","unstructured":"D. Wang , J. Zhang , W. Cao , J. Li , and Y. Zheng . 2018. When Will You Arrive Estimating Travel Time Based on Deep Neural Networks . In Proc. AAAI. D. Wang, J. Zhang, W. Cao, J. Li, and Y. Zheng. 2018. When Will You Arrive Estimating Travel Time Based on Deep Neural Networks. In Proc. AAAI."},{"key":"e_1_3_2_2_29_1","volume-title":"Proc. SIGKDD.","author":"Wei H.","unstructured":"H. Wei , G. Zheng , H. Yao , and Z. Li . 2018. IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control . In Proc. SIGKDD. H.Wei, G. Zheng, H. Yao, and Z. Li. 2018. IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control. In Proc. SIGKDD."},{"key":"e_1_3_2_2_30_1","volume-title":"Proc. CIKM.","author":"Yi X.","unstructured":"X. Yi , Z. Duan , T. Li , J. Zhang , T. Li , and Y. Zheng . 2019. CityTraffic: Modeling Citywide Traffic via Neural Memorization and Generalization Approach . In Proc. CIKM. X. Yi, Z. Duan, T. Li, J. Zhang, T. Li, and Y. Zheng. 2019. CityTraffic: Modeling Citywide Traffic via Neural Memorization and Generalization Approach. In Proc. CIKM."},{"key":"e_1_3_2_2_31_1","volume-title":"Proc. AAAI.","author":"Zhang J.","unstructured":"J. Zhang , Y. Zheng , and D. Qi . 2017. Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction . In Proc. AAAI. J. Zhang, Y. Zheng, and D. Qi. 2017. Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction. In Proc. AAAI."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"S. Zhang L. Qin and Y. Zheng. 2016. Effective and Efficient: Large-Scale Dynamic City Express. Transaction on Knowledge and Data Engineering (2016).  S. Zhang L. Qin and Y. Zheng. 2016. Effective and Efficient: Large-Scale Dynamic City Express. Transaction on Knowledge and Data Engineering (2016).","DOI":"10.1109\/TKDE.2016.2604806"}],"event":{"name":"CIKM '20: The 29th ACM International Conference on Information and Knowledge Management","location":"Virtual Event Ireland","acronym":"CIKM '20","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 29th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3340531.3411871","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3340531.3411871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:25:49Z","timestamp":1750206349000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3340531.3411871"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,19]]},"references-count":32,"alternative-id":["10.1145\/3340531.3411871","10.1145\/3340531"],"URL":"https:\/\/doi.org\/10.1145\/3340531.3411871","relation":{},"subject":[],"published":{"date-parts":[[2020,10,19]]},"assertion":[{"value":"2020-10-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}