{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:37:21Z","timestamp":1757608641537,"version":"3.44.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127287","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"2304-2310","source":"Crossref","is-referenced-by-count":0,"title":["Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances"],"prefix":"10.1109","author":[{"given":"Hanyang","family":"Hu","sequence":"first","affiliation":[{"name":"Simon Fraser University,Burnaby,BC,Canada,V5A 1S6"}]},{"given":"Xilun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA,15213"}]},{"given":"Xubo","family":"Lyu","sequence":"additional","affiliation":[{"name":"Simon Fraser University,Burnaby,BC,Canada,V5A 1S6"}]},{"given":"Mo","family":"Chen","sequence":"additional","affiliation":[{"name":"Simon Fraser University,Burnaby,BC,Canada,V5A 1S6"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341477"},{"key":"ref2","article-title":"Wococo: Learning whole-body humanoid control with sequential contacts","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610200"},{"key":"ref4","article-title":"Trust-worthy reinforcement learning against intrinsic vulnerabilities: Robustness, safety, and generalizability","author":"Xu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"734","article-title":"What went wrong? closing the sim-to-real gap via differentiable causal discovery","volume-title":"Conference on Robot Learning","author":"Huang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967695"},{"key":"ref7","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pinto","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-104941"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2728606.2728612"},{"key":"ref11","article-title":"Optimizeddp: An efficient, user-friendly library for optimal control and dynamic programming","author":"Bui","year":"2022","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref13","first-page":"26156","article-title":"Robust deep reinforcement learning through adversarial loss","volume":"34","author":"Oikarinen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","first-page":"1321","article-title":"Approximate dynamic programming for two-player zero-sum markov games","volume-title":"International Conference on Machine Learning","author":"Perolat","year":"2015"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","volume":"2","author":"Puterman","year":"1990","journal-title":"Handbooks in operations research and management science"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"ref17","first-page":"22056","article-title":"On the stability and convergence of robust adversarial reinforcement learning: A case study on linear quadratic systems","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Robust adversarial reinforcement learning via bounded rationality curricula","author":"Reddi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Robust reinforcement learning using adversarial populations","author":"Vinitsky","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/430"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102603"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(89)90360-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1201\/b10734"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1988.4789992"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(91)90022-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/9.256331"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611971132","volume-title":"Dynamic noncooperative game theory","author":"Ba\u015far","year":"1998"},{"key":"ref28","article-title":"H-infinity optimal control and related minimax design problems: a dynamic game approach","author":"Ba\u015far","year":"2008","journal-title":"Springer Science & Business Media"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/OJCSYS.2024.3449138"},{"key":"ref30","article-title":"Robust control lyapunov-value functions for nonlinear disturbed systems","author":"Gong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2025.01.005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2024.3408069"},{"key":"ref33","article-title":"Exact and efficient hamilton-jacobi-based guaranteed safety analysis via system decomposition","author":"Chen","year":"2016","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref35","first-page":"90","article-title":"Isaacs: Iterative soft adversarial actor-critic for safety","volume-title":"Learning for Dynamics and Control Conference","author":"Hsu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561949"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1983-0690039-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980264"},{"key":"ref39","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635857"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196132"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383438"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859219"},{"volume-title":"Quadrotor control: modeling, nonlinear control design, and simulation","year":"2015","author":"Sabatino","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2023.3344659"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127287.pdf?arnumber=11127287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:04:24Z","timestamp":1756879464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127287\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127287","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}