{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T05:26:06Z","timestamp":1736832366830,"version":"3.33.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62232016","62072442"],"award-info":[{"award-number":["62232016","62072442"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Basic Research Program of ISCAS","award":["ISCAS-JCZD-202304"],"award-info":[{"award-number":["ISCAS-JCZD-202304"]}]},{"name":"Major Program of ISCAS","award":["ISCAS-ZD-202302"],"award-info":[{"award-number":["ISCAS-ZD-202302"]}]},{"name":"Innovation Team 2024 ISCAS","award":["No. 2024-66"],"award-info":[{"award-number":["No. 2024-66"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cyber Security Agency under its National Cybersecurity R&D Programme","award":["NCRP25-P04-TAICeN"],"award-info":[{"award-number":["NCRP25-P04-TAICeN"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tse.2024.3491193","type":"journal-article","created":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T18:31:06Z","timestamp":1730831466000},"page":"66-81","source":"Crossref","is-referenced-by-count":0,"title":["Diversity-Oriented Testing for Competitive Game Agent via Constraint-Guided Adversarial Agent Training"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8514-2336","authenticated-orcid":false,"given":"Xuyan","family":"Ma","sequence":"first","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2854-4889","authenticated-orcid":false,"given":"Yawen","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9941-6713","authenticated-orcid":false,"given":"Junjie","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1288-6502","authenticated-orcid":false,"given":"Xiaofei","family":"Xie","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9285-3419","authenticated-orcid":false,"given":"Boyu","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1662-8883","authenticated-orcid":false,"given":"Yiguang","family":"Yan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8641-8130","authenticated-orcid":false,"given":"Shoubin","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6016-7360","authenticated-orcid":false,"given":"Fanjiang","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2618-5694","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1038\/s41586-023-06419-4"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/978-981-19-7784-8_10"},{"key":"ref3","first-page":"4190","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30: Annu. Conf. Neural Inf. Process. Syst.","author":"Lanctot","year":"2017"},{"key":"ref4","article-title":"Adversarial attacks on neural network policies","volume-title":"CoRR","volume":"abs\/1702.02284","author":"Huang","year":"2017"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/978-3-319-62416-7_19"},{"key":"ref6","article-title":"Adversarial policies: Attacking deep reinforcement learning","volume-title":"Proc. 8th Int. Conf. Learn. Representations (ICLR)","author":"Gleave","year":"2020"},{"key":"ref7","first-page":"1883","article-title":"Adversarial policy training against deep reinforcement learning","volume-title":"Proc. 30th USENIX Security Symposium, USENIX Security 2021","author":"Wu","year":"2021"},{"key":"ref8","first-page":"3910","article-title":"Adversarial policy learning in two-player competitive games","volume-title":"Proc. 38th Int. Conf. Mach. Learn., (ICML)","volume":"139","author":"Guo","year":"2021"},{"key":"ref9","first-page":"1285","article-title":"Imitating opponent to win: Adversarial policy imitation learning in two-player competitive games","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst., (AAMAS)","author":"Bui","year":"2023"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1145\/3597926.3598072"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ASE.2019.00077"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.24963\/ijcai.2020\/466"},{"key":"ref13","article-title":"Discovering diverse multi-agent strategic behavior via reward randomization","volume-title":"CoRR","volume":"abs\/2103.04564","author":"Tang","year":"2021"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/3533767.3534388"},{"key":"ref15","first-page":"17","article-title":"Policy diagnosis via measuring role diversity in cooperative multi-agent RL","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Hu","year":"2022"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref17","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn., (ICML)","volume":"70","author":"Achiam","year":"2017"},{"year":"2020","author":"Srinivasan","article-title":"Learning to be safe: Deep RL with a safety critic","key":"ref18"},{"key":"ref19","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","volume-title":"Proc. Knowl. Discovery Databases: Papers from AAAI Workshop","author":"Berndt","year":"1994"},{"volume-title":"Coding and Information Theory","year":"1986","author":"Hamming","key":"ref20"},{"year":"2014","author":"Kuleshov","article-title":"Algorithms for multi-armed bandit problems","key":"ref21"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1007\/978-3-642-24455-1_33"},{"year":"2021","author":"Hu","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","key":"ref23"},{"key":"ref24","first-page":"4292","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn., (ICML)","volume":"80","author":"Rashid","year":"2018"},{"year":"2022","author":"Han","article-title":"What is the solution for state-adversarial multi-agent reinforcement learning?","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICSE48619.2023.00155"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ASE56229.2023.00153"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1016\/j.neucom.2023.127191"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref30","first-page":"347","article-title":"Deepbillboard: systematic physical-world testing of autonomous driving systems","volume-title":"Proc. 42nd Int. Conf. Softw. Eng.","author":"Zhou","year":"2020"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1145\/3238147.3238187"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1145\/3180155.3180220"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICSTW52544.2021.00022"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/ICSE-Companion.2019.00119"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/ICSE-Companion.2019.00030"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1145\/3540250.3549111"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/SP.2017.49"},{"year":"2014","author":"Goodfellow","article-title":"Explaining and harnessing adversarial examples","key":"ref38"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/EuroSP.2016.36"},{"year":"2013","author":"Szegedy","article-title":"Intriguing properties of neural networks","key":"ref40"},{"key":"ref41","article-title":"Delving into adversarial attacks on deep policies","volume-title":"Proc. 5th Int. Conf. Learn. Representations (ICLR)","author":"Kos","year":"2017"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref43","first-page":"1010","article-title":"Characterizing attacks on deep reinforcement learning","volume-title":"Proc. 21st Int. Conf. Auton. Agents Multiagent Syst., (AAMAS)","author":"Pan","year":"2022"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1609\/aaai.v34i04.5887"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/10837580\/10742957.pdf?arnumber=10742957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T19:51:17Z","timestamp":1736797877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10742957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tse.2024.3491193","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"type":"print","value":"0098-5589"},{"type":"electronic","value":"1939-3520"},{"type":"electronic","value":"2326-3881"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}