{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T21:38:15Z","timestamp":1771105095633,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892908","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Curriculum Adversarial Training for Robust Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Junru","family":"Sheng","sequence":"first","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhai","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyan","family":"Dong","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Kang","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chixiao","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref30","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref10","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"4577","DOI":"10.1609\/aaai.v34i04.5887","article-title":"Spa-tiotemporally constrained action space attacks on deep reinforcement learning agents","volume":"34","author":"lee","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref12","article-title":"Real-time attacks against deep reinforcement learning policies","author":"tekgul","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2008.4586847"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"3803","DOI":"10.1109\/ICRA.2018.8460528","article-title":"Sim-to-real transfer of robotic control with dynamics randomization","author":"peng","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref17","article-title":"Robust reinforcement learning using adversarial populations","author":"vinitsky","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","first-page":"2817","article-title":"Robust adver-sarial reinforcement learning","author":"pinto","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref19","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","author":"tessler","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/353"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441797"},{"key":"ref27","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790981"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref8","article-title":"Robust reinforcement learning via adversarial training with langevin dynamics","author":"kamalaruban","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"christiano","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref9","article-title":"Challenges and countermeasures for adversarial attacks on deep reinforcement learning","author":"ilahi","year":"2021","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"ref1","first-page":"1329","article-title":"Bench-marking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref20","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref21","first-page":"1765","article-title":"Univer-sal adversarial perturbations","author":"moosavi-dezfooli","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref23","article-title":"Delving into adversarial attacks on deep policies","author":"kos","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.29007\/rft1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892908.pdf?arnumber=9892908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:26:51Z","timestamp":1667525211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892908","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}