{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T23:59:34Z","timestamp":1762300774336,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"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":[[2024,10,27]]},"DOI":"10.1145\/3691620.3694983","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T15:39:19Z","timestamp":1729265959000},"page":"14-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Can Cooperative Multi-Agent Reinforcement Learning Boost Automatic Web Testing? An Exploratory Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8722-3367","authenticated-orcid":false,"given":"Yujia","family":"Fan","sequence":"first","affiliation":[{"name":"Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, Guangdong, China"},{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8557-4681","authenticated-orcid":false,"given":"Sinan","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3096-4019","authenticated-orcid":false,"given":"Zebang","family":"Fei","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6548-4400","authenticated-orcid":false,"given":"Yao","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1555-6353","authenticated-orcid":false,"given":"Huaxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8147-8126","authenticated-orcid":false,"given":"Yepang","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, Guangdong, China"},{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. Flask Documentation --- flask.palletsprojects.com. https:\/\/flask.palletsprojects.com\/. [Accessed 27-03-2024]."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. SeleniumHQ\/selenium: A browser automation framework and ecosystem. --- github.com. https:\/\/github.com\/SeleniumHQ\/selenium\/. [Accessed 27-03-2024]."},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. Top Websites in the World - Most Visited & Popular Rankings - Semrush --- semrush.com. https:\/\/semrush.com\/website\/top\/. [Accessed 01-04-2024]."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(02)00030-X"},{"key":"e_1_3_2_1_5_1","volume-title":"Miles Brundage, and Anil Anthony Bharath.","author":"Arulkumaran Kai","year":"2017","unstructured":"Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, and Anil Anthony Bharath. 2017. A brief survey of deep reinforcement learning. arXiv preprint arXiv:1708.05866 (2017)."},{"volume-title":"A multi-agent based framework for collaborative testing on web services","author":"Bai Xiaoying","key":"e_1_3_2_1_6_1","unstructured":"Xiaoying Bai, Guilan Dai, Dezheng Xu, and Wei-Tek Tsai. 2006. A multi-agent based framework for collaborative testing on web services. In The Fourth IEEE Workshop on Software Technologies for Future Embedded and Ubiquitous Systems, and the Second International Workshop on Collaborative Computing, Integration, and Assurance (SEUS-WCCIA'06). IEEE, 6--pp."},{"key":"e_1_3_2_1_7_1","volume-title":"Fast abstracts of the 4th symposium on search-based software engineering (SSBSE","author":"Bauersfeld Sebastian","year":"2012","unstructured":"Sebastian Bauersfeld and Tanja Vos. 2012. A reinforcement learning approach to automated gui robustness testing. In Fast abstracts of the 4th symposium on search-based software engineering (SSBSE 2012). 7--12."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387903.3389308"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/11008941_25"},{"key":"e_1_3_2_1_10_1","volume-title":"6th International Conferenrence on Metaheuristics and nature inspired computing (META 2016)","author":"Esparcia-Alc\u00e1zar Anna I","year":"2016","unstructured":"Anna I Esparcia-Alc\u00e1zar, Francisco Almenar, Mirella Mart\u00ednez, Urko Rueda, and T Vos. 2016. Q-learning strategies for action selection in the TESTAR automated testing tool. 6th International Conferenrence on Metaheuristics and nature inspired computing (META 2016) (2016), 130--137."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSA59317.2023.00013"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"e_1_3_2_1_14_1","volume-title":"International conference on machine learning. PMLR, 1146--1155","author":"Foerster Jakob","year":"2017","unstructured":"Jakob Foerster, Nantas Nardelli, Gregory Farquhar, Triantafyllos Afouras, Philip HS Torr, Pushmeet Kohli, and Shimon Whiteson. 2017. Stabilising experience replay for deep multi-agent reinforcement learning. In International conference on machine learning. PMLR, 1146--1155."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"e_1_3_2_1_16_1","first-page":"709","article-title":"Dynamic programming for partially observable stochastic games","volume":"4","author":"Hansen Eric A","year":"2004","unstructured":"Eric A Hansen, Daniel S Bernstein, and Shlomo Zilberstein. 2004. Dynamic programming for partially observable stochastic games. In AAAI, Vol. 4. 709--715.","journal-title":"AAAI"},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in neural information processing systems 23","author":"Hasselt Hado","year":"2010","unstructured":"Hado Hasselt. 2010. Double Q-learning. Advances in neural information processing systems 23 (2010)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings 27th Annual International Computer Software and Applications Conference. COMPAC 2003. IEEE, 210--215","author":"Huo Qingning","year":"2003","unstructured":"Qingning Huo, Hong Zhu, and Sue Greenwood. 2003. A multi-agent software engineering environment for testing Web-based applications. In Proceedings 27th Annual International Computer Software and Applications Conference. COMPAC 2003. IEEE, 210--215."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2018.00020"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623344"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/274440.274441"},{"key":"e_1_3_2_1_22_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015","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":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091574.3091594"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2368731"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985979"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1538"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 2. Citeseer, 773--780","author":"Melo Francisco S","year":"2009","unstructured":"Francisco S Melo and Manuela Veloso. 2009. Learning of coordination: Exploiting sparse interactions in multiagent systems. In Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 2. Citeseer, 773--780."},{"volume-title":"Crawling Ajax by inferring user interface state changes. In 2008 eighth international conference on web engineering","author":"Mesbah Ali","key":"e_1_3_2_1_29_1","unstructured":"Ali Mesbah, Engin Bozdag, and Arie Van Deursen. 2008. Crawling Ajax by inferring user interface state changes. In 2008 eighth international conference on web engineering. IEEE, 122--134."},{"key":"e_1_3_2_1_30_1","volume-title":"International conference on machine learning. PMLR","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International conference on machine learning. PMLR, 1928--1937."},{"key":"e_1_3_2_1_31_1","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 al. 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529--533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion58688.2023.00024"},{"volume-title":"Grokking deep reinforcement learning","author":"Morales Miguel","key":"e_1_3_2_1_33_1","unstructured":"Miguel Morales. 2020. Grokking deep reinforcement learning. Manning Publications."},{"key":"e_1_3_2_1_34_1","volume-title":"Deep exploration via bootstrapped DQN. Advances in neural information processing systems 29","author":"Osband Ian","year":"2016","unstructured":"Ian Osband, Charles Blundell, Alexander Pritzel, and Benjamin Van Roy. 2016. Deep exploration via bootstrapped DQN. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397354"},{"key":"e_1_3_2_1_36_1","volume-title":"David Feil-Seifer, and Aria Nefian.","author":"Pham Huy Xuan","year":"2018","unstructured":"Huy Xuan Pham, Hung Manh La, David Feil-Seifer, and Aria Nefian. 2018. Co-operative and distributed reinforcement learning of drones for field coverage. arXiv preprint arXiv:1803.07250 (2018)."},{"key":"e_1_3_2_1_37_1","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid Tabish","year":"2020","unstructured":"Tabish Rashid, Mikayel Samvelyan, Christian Schroeder De Witt, Gregory Farquhar, Jakob Foerster, and Shimon Whiteson. 2020. Monotonic value function factorisation for deep multi-agent reinforcement learning. Journal of Machine Learning Research 21, 178 (2020), 1--51.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111512"},{"key":"e_1_3_2_1_39_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al.","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. nature 529, 7587 (2016), 484--489."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"David Silver Julian Schrittwieser Karen Simonyan Ioannis Antonoglou Aja Huang Arthur Guez Thomas Hubert Lucas Baker Matthew Lai Adrian Bolton et al. 2017. Mastering the game of go without human knowledge. nature 550 7676 (2017) 354--359.","DOI":"10.1038\/nature24270"},{"key":"e_1_3_2_1_41_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)."},{"volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","key":"e_1_3_2_1_42_1","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091529.3091572"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 9th ACM SIGSOFT International Workshop on Automating TEST Case Design, Selection, and Evaluation. 31--37","author":"Tuyet Vuong Thi Anh","year":"2018","unstructured":"Thi Anh Tuyet Vuong and Shingo Takada. 2018. A reinforcement learning based approach to automated testing of android applications. In Proceedings of the 9th ACM SIGSOFT International Workshop on Automating TEST Case Design, Selection, and Evaluation. 31--37."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Thi Anh Tuyet Vuong and Shingo Takada. 2019. Semantic Analysis for Deep Q-Network in Android GUI Testing.. In SEKE. 123--170.","DOI":"10.18293\/SEKE2019-080"},{"key":"e_1_3_2_1_46_1","volume-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization. Advances in Neural Information Processing Systems 31","author":"Wai Hoi-To","year":"2018","unstructured":"Hoi-To Wai, Zhuoran Yang, Zhaoran Wang, and Mingyi Hong. 2018. Multi-agent reinforcement learning via double averaging primal-dual optimization. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_1_47_1","volume-title":"Machine learning 8","author":"Watkins Christopher JCH","year":"1992","unstructured":"Christopher JCH Watkins and Peter Dayan. 1992. Q-learning. Machine learning 8 (1992), 279--292."},{"key":"e_1_3_2_1_48_1","volume-title":"An overview of multi-agent reinforcement learning from game theoretical perspective. arXiv preprint arXiv:2011.00583","author":"Yang Yaodong","year":"2020","unstructured":"Yaodong Yang and Jun Wang. 2020. An overview of multi-agent reinforcement learning from game theoretical perspective. arXiv preprint arXiv:2011.00583 (2020)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00139"},{"key":"e_1_3_2_1_50_1","volume-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of reinforcement learning and control","author":"Zhang Kaiqing","year":"2021","unstructured":"Kaiqing Zhang, Zhuoran Yang, and Tamer Ba\u015far. 2021. Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of reinforcement learning and control (2021), 321--384."},{"key":"e_1_3_2_1_51_1","volume-title":"International Conference on Machine Learning. PMLR, 5872--5881","author":"Zhang Kaiqing","year":"2018","unstructured":"Kaiqing Zhang, Zhuoran Yang, Han Liu, Tong Zhang, and Tamer Basar. 2018. Fully decentralized multi-agent reinforcement learning with networked agents. In International Conference on Machine Learning. PMLR, 5872--5881."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00048"}],"event":{"name":"ASE '24: 39th IEEE\/ACM International Conference on Automated Software Engineering","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"],"location":"Sacramento CA USA","acronym":"ASE '24"},"container-title":["Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691620.3694983","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3691620.3694983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:06Z","timestamp":1750291446000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691620.3694983"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":51,"alternative-id":["10.1145\/3691620.3694983","10.1145\/3691620"],"URL":"https:\/\/doi.org\/10.1145\/3691620.3694983","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2024-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}