{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T04:08:04Z","timestamp":1768709284302,"version":"3.49.0"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20220071"],"award-info":[{"award-number":["BX20220071"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipality Science and Technology Major Project","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]},{"name":"National Key R&D Program of China","award":["2021ZD0113502"],"award-info":[{"award-number":["2021ZD0113502"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/lra.2022.3220531","type":"journal-article","created":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T20:32:09Z","timestamp":1667939529000},"page":"12562-12568","source":"Crossref","is-referenced-by-count":9,"title":["Robust Adaptive Ensemble Adversary Reinforcement Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1374-7969","authenticated-orcid":false,"given":"Peng","family":"Zhai","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taixian","family":"Hou","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3920-8362","authenticated-orcid":false,"given":"Xiaopeng","family":"Ji","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9459-1889","authenticated-orcid":false,"given":"Zhiyan","family":"Dong","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0467-4347","authenticated-orcid":false,"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"tielong","year":"1996","journal-title":"H? control theory and application"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref12","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","author":"tessler","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1249"},{"key":"ref14","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","author":"lan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920231"},{"key":"ref16","article-title":"Model-ensemble trust-region policy optimization","author":"kurutach","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","article-title":"Multi-generator generative adversarial nets","author":"hoang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","article-title":"Stabilizing GAN training with multiple random projections","author":"neyshabur","year":"2017"},{"key":"ref19","article-title":"Extending robust adversarial reinforcement learning considering adaptation and diversity","author":"shioya","year":"0","journal-title":"Proc Int Conf Learn Representations Workshop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062303"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref8","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196611"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056444"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20481"},{"key":"ref20","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID lagrangian methods","author":"stooke","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00889"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963426"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_26"},{"key":"ref23","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9831196\/09942298.pdf?arnumber=9942298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:27:38Z","timestamp":1670873258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9942298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":24,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3220531","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}