{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:20:17Z","timestamp":1780636817928,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62136008"],"award-info":[{"award-number":["62136008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103104"],"award-info":[{"award-number":["62103104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173251"],"award-info":[{"award-number":["62173251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["2024M750422"],"award-info":[{"award-number":["2024M750422"]}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20240144"],"award-info":[{"award-number":["GZB20240144"]}]},{"name":"Jiangsu Funding Program for Excellent Postdoctorial Talent","award":["2024ZB047"],"award-info":[{"award-number":["2024ZB047"]}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20231417"],"award-info":[{"award-number":["BK20231417"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tai.2024.3499938","type":"journal-article","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T13:54:00Z","timestamp":1731678840000},"page":"874-884","source":"Crossref","is-referenced-by-count":4,"title":["Active Robust Adversarial Reinforcement Learning Under Temporally Coupled Perturbations"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2898-9538","authenticated-orcid":false,"given":"Jiacheng","family":"Yang","sequence":"first","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8002-8131","authenticated-orcid":false,"given":"Yuanda","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6737-1381","authenticated-orcid":false,"given":"Lu","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2510-1188","authenticated-orcid":false,"given":"Lei","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"35763","article-title":"Policy gradient in robust mdps with global convergence guarantee","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/380"},{"key":"ref3","first-page":"7193","article-title":"Online robust reinforcement learning with model uncertainty","volume":"34","author":"Wang","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2884725"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/YAC59482.2023.10401706"},{"key":"ref6","article-title":"Robust reinforcement learning for continuous control with model misspecification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mankowitz","year":"2020"},{"key":"ref7","first-page":"6967","article-title":"Max-min off-policy actor-critic method focusing on worst-case robustness to model misspecification","volume":"35","author":"Tanabe","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref8","first-page":"8707","article-title":"Deep reinforcement learning with robust and smooth policy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shen","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10739-w"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3237665"},{"key":"ref11","article-title":"Solving Rubik\u2019s cube with a robot hand","author":"Akkaya","year":"2019"},{"key":"ref12","first-page":"1162","article-title":"Active domain randomization","volume-title":"Proc. Conf. Robot Learn.","author":"Mehta","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref14","first-page":"32783","article-title":"Adversarial learning of distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sui","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref16","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume":"33","author":"Zhang","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref17","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Pattanaik","year":"2018"},{"key":"ref18","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto","year":"2017"},{"key":"ref19","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tessler","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20481"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/51"},{"key":"ref23","first-page":"66328","article-title":"Seeing is not believing: Robust reinforcement learning against spurious correlation","volume":"36","author":"Ding","year":"2023","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref24","article-title":"Game-theoretic robust reinforcement learning handles temporally-coupled perturbations","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Liang","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206442"},{"key":"ref26","article-title":"Robust reinforcement learning using adversarial populations","author":"Vinitsky","year":"2020"},{"key":"ref27","first-page":"1321","article-title":"Approximate dynamic programming for two-player zero-sum Markov games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Perolat","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213566"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref31","first-page":"8127","article-title":"Robust reinforcement learning via adversarial training with langevin dynamics","volume":"33","author":"Kamalaruban","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5887"},{"key":"ref33","article-title":"Certifiably robust policy learning against adversarial multi-agent communication","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Sun","year":"2023"},{"key":"ref34","article-title":"Robust reinforcement learning on state observations with learned optimal adversary","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2021"},{"key":"ref35","first-page":"22547","article-title":"Efficient adversarial training without attacking: Worst-case-aware robust reinforcement learning","volume":"35","author":"Liang","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref37","first-page":"26156","article-title":"Robust deep reinforcement learning through adversarial loss","volume":"34","author":"Oikarinen","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref38","article-title":"Who is the strongest enemy? Towards optimal and efficient evasion attacks in deep RL","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sun","year":"2022"},{"key":"ref39","first-page":"3756","article-title":"Tactics of adversarial attack on deep reinforcement learning agents","volume-title":"Proc. 26th Int. Joint Conf. Artif. Intell.","author":"Lin","year":"2017"},{"key":"ref40","article-title":"Adversarial policies: Attacking deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gleave","year":"2020"},{"key":"ref41","first-page":"1328","article-title":"Certified adversarial robustness for deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"L\u00fctjens","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147846"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3274908"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1145\/3450267.3450537","article-title":"Query-based targeted action-space adversarial policies on deep reinforcement learning agents","volume-title":"Proc. ACM\/IEEE 12th Int. Conf. Cyber-Phys. Syst.","author":"Lee","year":"2021"},{"key":"ref46","first-page":"7216","article-title":"Non-stationary Markov decision processes, a worst-case approach using model-based reinforcement learning","volume":"32","author":"Lecarpentier","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref47","first-page":"81","article-title":"Attribution of adversarial attacks via multi-task learning","volume-title":"Proc. Int. Conf. Neural Inf. Process.","author":"Guo","year":"2023"},{"key":"ref48","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref49","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref52","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500450"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10946214\/10754649.pdf?arnumber=10754649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:01:10Z","timestamp":1764270070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10754649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":53,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3499938","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}