{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T10:11:48Z","timestamp":1780395108331,"version":"3.54.1"},"publisher-location":"New York, New York, USA","reference-count":50,"publisher":"ACM Press","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation of China","award":["61272227"],"award-info":[{"award-number":["61272227"]}]},{"name":"National Science Foundation of China","award":["61332007"],"award-info":[{"award-number":["61332007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1145\/3178876.3186165","type":"proceedings-article","created":{"date-parts":[[2018,4,13]],"date-time":"2018-04-13T15:53:48Z","timestamp":1523634828000},"page":"1939-1948","source":"Crossref","is-referenced-by-count":56,"title":["Learning to Collaborate"],"prefix":"10.1145","author":[{"given":"Jun","family":"Feng","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minlie","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shichen","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwu","family":"Ou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhirong","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","reference":[{"key":"key-10.1145\/3178876.3186165-1","unstructured":"Leif Azzopardi and Guido Zuccon . 2016. Advances in formal models of search and search behaviour Proceedings of the 2016 ACM on International Conference on the Theory of Information Retrieval. ACM, 1--4."},{"key":"key-10.1145\/3178876.3186165-2","doi-asserted-by":"crossref","unstructured":"Chris Burges, Tal Shaked, Erin Renshaw, Ari Lazier, Matt Deeds, Nicole Hamilton, and Greg Hullender . 2005. Learning to rank using gradient descent. In Proceedings of the 22nd international conference on Machine learning. ACM, 89--96.","DOI":"10.1145\/1102351.1102363"},{"key":"key-10.1145\/3178876.3186165-3","doi-asserted-by":"crossref","unstructured":"Christopher J Burges, Robert Ragno, and Quoc V Le . 2007. Learning to rank with nonsmooth cost functions. In NIPS. 193--200.","DOI":"10.7551\/mitpress\/7503.003.0029"},{"key":"key-10.1145\/3178876.3186165-4","doi-asserted-by":"crossref","unstructured":"Lucian Busoniu, Robert Babuska, and Bart De Schutter . 2008. A comprehensive survey of multiagent reinforcement learning. IEEE Transactions on Systems, Man, And Cybernetics-Part C: Applications and Reviews, 38 (2), 2008 (2008).","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"key-10.1145\/3178876.3186165-5","unstructured":"Lucian Busoniu, Robert Babuvska, and Bart De Schutter . 2010. Multi-agent reinforcement learning: An overview. Innovations in multi-agent systems and applications-1 Vol. 310 (2010), 183--221."},{"key":"key-10.1145\/3178876.3186165-6","doi-asserted-by":"crossref","unstructured":"Zhe Cao, Tao Qin, Tie-Yan Liu, Ming-Feng Tsai, and Hang Li . 2007. Learning to rank: from pairwise approach to listwise approach ICML. ACM, 129--136.","DOI":"10.1145\/1273496.1273513"},{"key":"key-10.1145\/3178876.3186165-7","doi-asserted-by":"crossref","unstructured":"Jaime Carbonell and Jade Goldstein . 1998. The use of MMR, diversity-based reranking for reordering documents and producing summaries. In the 21st ACM SIGIR. ACM, 335--336.","DOI":"10.1145\/290941.291025"},{"key":"key-10.1145\/3178876.3186165-8","unstructured":"Jack Clark . Retrieved 28 October2015. Google Turning Its Lucrative Web Search Over to AI Machines. Bloomberg Business (. Retrieved 28 October2015)."},{"key":"key-10.1145\/3178876.3186165-9","unstructured":"Caroline Claus and Craig Boutilier . 1998. The dynamics of reinforcement learning in cooperative multiagent systems. AAAI\/IAAI Vol. 1998 (1998), 746--752."},{"key":"key-10.1145\/3178876.3186165-10","doi-asserted-by":"crossref","unstructured":"Paul Covington, Jay Adams, and Emre Sargin . 2016. Deep Neural Networks for YouTube Recommendations. In ACM Conference on Recommender Systems. 191--198.","DOI":"10.1145\/2959100.2959190"},{"key":"key-10.1145\/3178876.3186165-11","doi-asserted-by":"crossref","unstructured":"Carl Davidson and Raymond Deneckere . 1986. Long-run competition in capacity, short-run competition in price, and the Cournot model. The Rand Journal of Economics (1986), 404--415.","DOI":"10.2307\/2555720"},{"key":"key-10.1145\/3178876.3186165-12","unstructured":"Jakob Foerster, Yannis M Assael, Nando de Freitas, and Shimon Whiteson . 2016. Learning to communicate with deep multi-agent reinforcement learning Advances in Neural Information Processing Systems. 2137--2145."},{"key":"key-10.1145\/3178876.3186165-13","doi-asserted-by":"crossref","unstructured":"Jakob Foerster, Gregory Farquhar, Triantafyllos Afouras, Nantas Nardelli, and Shimon Whiteson . 2017. Counterfactual Multi-Agent Policy Gradients. arXiv preprint arXiv:1705.08926 (2017).","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"key-10.1145\/3178876.3186165-14","doi-asserted-by":"crossref","unstructured":"Xiubo Geng, Tie-Yan Liu, Tao Qin, and Hang Li . 2007. Feature selection for ranking. In Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval. ACM, 407--414.","DOI":"10.1145\/1277741.1277811"},{"key":"key-10.1145\/3178876.3186165-15","unstructured":"Fredric C Gey . 1994. Inferring probability of relevance using the method of logistic regression Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval. Springer-Verlag New York, Inc., 222--231."},{"key":"key-10.1145\/3178876.3186165-16","doi-asserted-by":"crossref","unstructured":"Jayesh K Gupta, Maxim Egorov, and Mykel Kochenderfer . 2017. Cooperative multiagent control using deep reinforcement learning Proceedings of the Adaptive and Learning Agents workshop (at AAMAS 2017).","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"key-10.1145\/3178876.3186165-17","doi-asserted-by":"crossref","unstructured":"Saurabh Gupta, Sayan Pathak, and Bivas Mitra . 2015. Complementary Usage of Tips and Reviews for Location Recommendation in Yelp. Springer International Publishing. 1003--1003 pages.","DOI":"10.1007\/978-3-319-18032-8_56"},{"key":"key-10.1145\/3178876.3186165-18","unstructured":"Matthew Hausknecht and Peter Stone . 2015. Deep recurrent q-learning for partially observable mdps. (2015)."},{"key":"key-10.1145\/3178876.3186165-19","unstructured":"Jiyin He, Vera Hollink, and Arjen de Vries . 2012. Combining implicit and explicit topic representations for result diversification the 35th ACM SIGIR. ACM, 851--860."},{"key":"key-10.1145\/3178876.3186165-20","unstructured":"Nicolas Heess, Gregory Wayne, David Silver, Tim Lillicrap, Tom Erez, and Yuval Tassa . 2015. Learning continuous control policies by stochastic value gradients NIPS. 2944--2952."},{"key":"key-10.1145\/3178876.3186165-21","doi-asserted-by":"crossref","unstructured":"Sepp Hochreiter and Jürgen Schmidhuber . 1997. Long short-term memory. Neural computation Vol. 9, 8 (1997), 1735--1780.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"key-10.1145\/3178876.3186165-22","unstructured":"Junling Hu, Michael P Wellman, et almbox. . 1998. Multiagent reinforcement learning: theoretical framework and an algorithm. ICML, Vol. Vol. 98. 242--250."},{"key":"key-10.1145\/3178876.3186165-23","unstructured":"Shubhra Kanti Karmaker Santu, Parikshit Sondhi, and ChengXiang Zhai . 2017. On Application of Learning to Rank for E-Commerce Search Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 475--484."},{"key":"key-10.1145\/3178876.3186165-24","doi-asserted-by":"crossref","unstructured":"Krishnaram Kenthapadi, Krishnaram Kenthapadi, and Krishnaram Kenthapadi . 2017. LiJAR: A System for Job Application Redistribution towards Efficient Career Marketplace ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1397--1406.","DOI":"10.1145\/3097983.3098028"},{"key":"key-10.1145\/3178876.3186165-25","unstructured":"Vijay R Konda and John N Tsitsiklis . 2000. Actor-critic algorithms. In Advances in neural information processing systems. 1008--1014."},{"key":"key-10.1145\/3178876.3186165-26","unstructured":"Martin Lauer and Martin Riedmiller . 2000. An algorithm for distributed reinforcement learning in cooperative multi-agent systems In Proceedings of the Seventeenth International Conference on Machine Learning. Citeseer."},{"key":"key-10.1145\/3178876.3186165-27","doi-asserted-by":"crossref","unstructured":"Hang Li . 2014. Learning to rank for information retrieval and natural language processing. Synthesis Lectures on Human Language Technologies Vol. 7, 3 (2014), 1--121.","DOI":"10.2200\/S00607ED2V01Y201410HLT026"},{"key":"key-10.1145\/3178876.3186165-28","doi-asserted-by":"crossref","unstructured":"Lihong Li, Wei Chu, John Langford, and Xuanhui Wang . 2011. Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms. In Proceedings of the fourth ACM international conference on Web search and data mining. ACM, 297--306.","DOI":"10.1145\/1935826.1935878"},{"key":"key-10.1145\/3178876.3186165-29","unstructured":"Ping Li, Qiang Wu, and Christopher J Burges . 2008. Mcrank: Learning to rank using multiple classification and gradient boosting Advances in neural information processing systems. 897--904."},{"key":"key-10.1145\/3178876.3186165-30","unstructured":"Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra . 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"key-10.1145\/3178876.3186165-31","unstructured":"Michael L Littman . 1994. Markov games as a framework for multi-agent reinforcement learning Proceedings of the eleventh international conference on machine learning, Vol. Vol. 157. 157--163."},{"key":"key-10.1145\/3178876.3186165-32","doi-asserted-by":"crossref","unstructured":"Shichen Liu, Fei Xiao, Wenwu Ou, and Luo Si . 2017. Cascade Ranking for Operational E-commerce Search. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada, August 13 - 17, 2017. 1557--1565.","DOI":"10.1145\/3097983.3098011"},{"key":"key-10.1145\/3178876.3186165-33","unstructured":"Tie-Yan Liu et almbox. . 2009. Learning to rank for information retrieval. Foundations and Trends® in Information Retrieval Vol. 3, 3 (2009), 225--331."},{"key":"key-10.1145\/3178876.3186165-34","doi-asserted-by":"crossref","unstructured":"Craig Macdonald, Rodrygo LT Santos, and Iadh Ounis . 2013. The whens and hows of learning to rank for web search. Information Retrieval Vol. 16, 5 (2013), 584--628.","DOI":"10.1007\/s10791-012-9209-9"},{"key":"key-10.1145\/3178876.3186165-35","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et almbox. . 2015. Human-level control through deep reinforcement learning. Nature Vol. 518, 7540 (2015), 529--533.","DOI":"10.1038\/nature14236"},{"key":"key-10.1145\/3178876.3186165-36","doi-asserted-by":"crossref","unstructured":"Liviu Panait and Sean Luke . 2005. Cooperative multi-agent learning: The state of the art. Autonomous agents and multi-agent systems Vol. 11, 3 (2005), 387--434.","DOI":"10.1007\/s10458-005-2631-2"},{"key":"key-10.1145\/3178876.3186165-37","doi-asserted-by":"crossref","unstructured":"Tao Qin, Xu-Dong Zhang, De-Sheng Wang, Tie-Yan Liu, Wei Lai, and Hang Li . 2007. Ranking with multiple hyperplanes. In Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval. ACM, 279--286.","DOI":"10.1145\/1277741.1277791"},{"key":"key-10.1145\/3178876.3186165-38","unstructured":"Juan C Santamar'ıa, Richard S Sutton, and Ashwin Ram . 1997. Experiments with reinforcement learning in problems with continuous state and action spaces. Adaptive behavior Vol. 6, 2 (1997), 163--217."},{"key":"key-10.1145\/3178876.3186165-39","doi-asserted-by":"crossref","unstructured":"Bichen Shi, Georgiana Ifrim, and Neil Hurley . 2016. Learning-to-rank for real-time high-precision hashtag recommendation for streaming news. In Proceedings of the 25th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 1191--1202.","DOI":"10.1145\/2872427.2882982"},{"key":"key-10.1145\/3178876.3186165-40","doi-asserted-by":"crossref","unstructured":"Yue Shi, Martha Larson, and Alan Hanjalic . 2010. List-wise learning to rank with matrix factorization for collaborative filtering. In Proceedings of the fourth ACM conference on Recommender systems. ACM, 269--272.","DOI":"10.1145\/1864708.1864764"},{"key":"key-10.1145\/3178876.3186165-41","unstructured":"Peter Sunehag, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, et almbox. . 2017. Value-Decomposition Networks For Cooperative Multi-Agent Learning. arXiv preprint arXiv:1706.05296 (2017)."},{"key":"key-10.1145\/3178876.3186165-42","unstructured":"Richard S Sutton and Andrew G Barto . 1998. Reinforcement learning: An introduction. Vol. Vol. 1. MIT press Cambridge."},{"key":"key-10.1145\/3178876.3186165-43","unstructured":"Richard S Sutton, David A McAllester, Satinder P Singh, and Yishay Mansour . 2000. Policy gradient methods for reinforcement learning with function approximation NIPS. 1057--1063."},{"key":"key-10.1145\/3178876.3186165-44","doi-asserted-by":"crossref","unstructured":"Paul Viola and Michael Jones . 2001. Rapid object detection using a boosted cascade of simple features Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, Vol. Vol. 1. IEEE, I--I.","DOI":"10.1109\/CVPR.2001.990517"},{"key":"key-10.1145\/3178876.3186165-45","doi-asserted-by":"crossref","unstructured":"Lidan Wang, Jimmy Lin, and Donald Metzler . 2010 a. Learning to efficiently rank. In Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval. ACM, 138--145.","DOI":"10.1145\/1835449.1835475"},{"key":"key-10.1145\/3178876.3186165-46","unstructured":"Lidan Wang, Jimmy Lin, and Donald Metzler . 2011. A cascade ranking model for efficient ranked retrieval Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval. ACM, 105--114."},{"key":"key-10.1145\/3178876.3186165-47","doi-asserted-by":"crossref","unstructured":"Lidan Wang, Donald Metzler, and Jimmy Lin . 2010 b. Ranking under temporal constraints. In Proceedings of the 19th ACM international conference on Information and knowledge management. ACM, 79--88.","DOI":"10.1145\/1871437.1871452"},{"key":"key-10.1145\/3178876.3186165-48","unstructured":"Christopher JCH Watkins and Peter Dayan . 1992. Q-learning. Machine learning Vol. 8, 3--4 (1992), 279--292."},{"key":"key-10.1145\/3178876.3186165-49","unstructured":"Long Xia, Jun Xu, Yanyan Lan, Jiafeng Guo, Wei Zeng, and Xueqi Cheng . 2017. Adapting Markov Decision Process for Search Result Diversification Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, Tokyo, Japan, August 7--11, 2017. 535--544."},{"key":"key-10.1145\/3178876.3186165-50","doi-asserted-by":"crossref","unstructured":"Dawei Yin, Yuening Hu, Jiliang Tang, Tim Daly, Mianwei Zhou, Hua Ouyang, Jianhui Chen, Changsung Kang, Hongbo Deng, Chikashi Nobata, et almbox. . 2016. Ranking relevance in yahoo search. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 323--332.","DOI":"10.1145\/2939672.2939677"}],"event":{"name":"the 2018 World Wide Web Conference","location":"Lyon, France","acronym":"WWW '18","number":"2018","sponsor":["SIGWEB, ACM Special Interest Group on Hypertext, Hypermedia, and Web","IW3C2, International World Wide Web Conference Committee"],"start":{"date-parts":[[2018,4,23]]},"end":{"date-parts":[[2018,4,27]]}},"container-title":["Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3178876.3186165","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=3186165&ftid=1957348&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T17:28:11Z","timestamp":1751563691000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=3178876.3186165"}},"subtitle":["Multi-Scenario Ranking via Multi-Agent Reinforcement Learning"],"proceedings-subject":"World Wide Web","short-title":[],"issued":{"date-parts":[[2018]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1145\/3178876.3186165","relation":{},"subject":[],"published":{"date-parts":[[2018]]}}}