{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T22:06:55Z","timestamp":1772143615719,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007103","name":"Scientific Systems Company","doi-asserted-by":"publisher","award":["SC-1661-04"],"award-info":[{"award-number":["SC-1661-04"]}],"id":[{"id":"10.13039\/100007103","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005423","name":"ARL","doi-asserted-by":"publisher","award":["W911NF-17-2-0181"],"award-info":[{"award-number":["W911NF-17-2-0181"]}],"id":[{"id":"10.13039\/100005423","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812321","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"5503-5510","source":"Crossref","is-referenced-by-count":7,"title":["ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation"],"prefix":"10.1109","author":[{"given":"Chuangchuang","family":"Sun","sequence":"first","affiliation":[{"name":"Mississippi State University,Department of Aerospace Engineering,MS,39762"}]},{"given":"Dong-Ki","family":"Kim","sequence":"additional","affiliation":[{"name":"Laboratory for Information & Decision Systems, Massachusetts Institute of Technology,Cambridge,MA,02139"}]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[{"name":"Laboratory for Information & Decision Systems, Massachusetts Institute of Technology,Cambridge,MA,02139"}]}],"member":"263","reference":[{"key":"ref39","first-page":"5286","article-title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","author":"wong","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref38","article-title":"A convex relaxation barrier to tight ro-bust verification of neural networks","author":"salman","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref33","article-title":"Efficient formal safety analysis of neural networks","author":"wang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref32","first-page":"6","article-title":"Fast and effective robustness certification","volume":"1","author":"singh","year":"2018","journal-title":"NeurIPS"},{"key":"ref31","first-page":"5276","article-title":"Towards fast computation of certified robustness for relu networks","author":"weng","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_5"},{"key":"ref37","first-page":"497","article-title":"Efficient neural network verification with exactness characterization","author":"dvijotham","year":"2020","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref36","article-title":"Semidefi-nite relaxations for certifying robustness to adversarial examples","author":"raghunathan","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref35","article-title":"Efficient neural network robustness certifi-cation with general activation functions","author":"zhang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Boosting robustness certification of neural networks","author":"singh","year":"2019","journal-title":"ICLR (Poster)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref40","article-title":"Automatic perturbation analysis for scalable certified robustness and beyond","volume":"33","author":"xu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"The complexity of constrained min-max optimization","author":"daskalakis","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"A survey of learning in multi agent environments: Dealing with non-stationarity","volume":"abs 1707 9183","author":"hernandez-leal","year":"2017","journal-title":"CoRR"},{"key":"ref13","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume":"80","author":"yang","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref14","article-title":"Probabilistic recursive reasoning for multi -agent reinforcement learning","author":"wen","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","first-page":"620","article-title":"Learning hierarchical teaching policies for cooperative agents","author":"kim","year":"2020","journal-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems ser AAMAS '20"},{"key":"ref16","first-page":"232","article-title":"Learning Nash Equilibrium for General-Sum Markov Games from Batch Data","volume":"54","author":"perolat","year":"0","journal-title":"Proceedings of the 20th international Conference on Artificial Intelligence and Statistics ser Proceedings of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/37"},{"key":"ref18","author":"osborne","year":"2004","journal-title":"An Introduction to Game Theory"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref28","first-page":"1524","article-title":"DiCE: The infinitely differentiable Monte Carlo estimator","volume":"80","author":"foerster","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CASE.2011.6042493"},{"key":"ref27","first-page":"122","article-title":"Learning with opponent-learning awareness","author":"foerster","year":"2018","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3072021"},{"key":"ref6","first-page":"5541","article-title":"A policy gradient algorithm for learning to learn in multiagent reinforcement learning","volume":"139","author":"kim","year":"0","journal-title":"Proceedings of the 38th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref29","article-title":"Stable opponent shaping in differentiable games","author":"letcher","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref5","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","author":"al-shedivat","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref8","article-title":"Counterfactual multi -agent policy gradi-ents","volume":"32","author":"foerster","year":"2018","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI)"},{"key":"ref7","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917719333"},{"key":"ref9","article-title":"Adversarial policies: Attacking deep rein-forcement learning","author":"gleave","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72665-4_6"},{"key":"ref20","first-page":"1328","article-title":"Certified adversarial robustness for deep reinforcement learning","author":"l\u00fctjens","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1609\/icaps.v31i1.16006","article-title":"Robust opponent modeling via adversarial ensemble reinforcement learning","volume":"31","author":"shen","year":"2021","journal-title":"Proceedings of the International Conference on Automated Planning and Scheduling"},{"key":"ref42","article-title":"On the effectiveness of interval bound propagation for training verifiably robust models","author":"gowal","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref41","article-title":"Towards stable and efficient training of verifiably robust neural networks","author":"zhang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"Population based training of neural networks","volume":"abs 1711 9846","author":"jaderberg","year":"2017","journal-title":"CoRR"},{"key":"ref26","article-title":"Multi-agent learning with policy prediction","author":"zhang","year":"2010","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI)"},{"key":"ref25","article-title":"Emergent complexity via multi-agent competition","author":"bansal","year":"2018","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812321.pdf?arnumber=9812321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:06:22Z","timestamp":1727568382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812321\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812321","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}