{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:04:41Z","timestamp":1780765481293,"version":"3.54.1"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610498","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"9197-9204","source":"Crossref","is-referenced-by-count":11,"title":["Learning Vision-based Pursuit-Evasion Robot Policies"],"prefix":"10.1109","author":[{"given":"Andrea","family":"Bajcsy","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Loquercio","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish","family":"Kumar","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jitendra","family":"Malik","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.054"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160760"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.056"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abg5810"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature12295"},{"key":"ref10","first-page":"66","article-title":"Learning by cheating","volume-title":"Conference on Robot Learning","author":"Chen"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611971132","volume-title":"Dynamic noncooperative game theory","author":"Ba\u015far","year":"1998"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref13","article-title":"Differential games i: Introduction","volume-title":"RAND CORP SANTA MONICA CA SANTA MONICA, Tech. Rep.","author":"Isaacs","year":"1954"},{"key":"ref14","volume-title":"Differential games: a mathematical theory with applications to warfare and pursuit, control and optimization","author":"Isaacs","year":"1999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.851439"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref19","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pinto"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341777"},{"key":"ref22","article-title":"Isaacs: Iterative soft adversarial actor-critic for safety","volume-title":"L4DC","author":"Hsu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.066"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075376"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/0221051"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364906065023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2006721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/EBCCSP.2016.7605233"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812083"},{"key":"ref30","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5636"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref33","first-page":"18 808","article-title":"Influencing long-term behavior in multiagent reinforcement learning","volume":"35","author":"Kim","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","article-title":"Emergent tool use from multi-agent interaction","volume-title":"Machine Learning","author":"Baker","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"issue":"6624","key":"ref36","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1126\/science.ade9097","article-title":"Human-level play in the game of diplomacy by combining language models with strategic reasoning","volume":"378","author":"(FAIR)\u2020","year":"2022","journal-title":"Science"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2899570"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2019.2952590","article-title":"AD-VAT: An asymmetric dueling mechanism for learning visual active tracking","volume-title":"International Conference on Learning Representations","author":"Zhong"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25482"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(99)00033-0"},{"key":"ref42","first-page":"575","article-title":"Learning latent representations to influence multi-agent interaction","volume-title":"Conference on robot learning","author":"Xie"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981601"},{"key":"ref44","first-page":"1132","article-title":"Influencing towards stable multi-agent interactions","volume-title":"Conference on robot learning","author":"Wang"},{"key":"ref45","first-page":"2105","article-title":"Learning representations that enable generalization in assistive tasks","volume-title":"Conference on Robot Learning","author":"He"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10341936"},{"key":"ref47","article-title":"Multi-agent manipulation via locomotion using hierarchical sim2real","volume-title":"Conference on Robot Learning","author":"Nachum"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160914"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341987"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref51","article-title":"Zed 2 camera"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341579"},{"key":"ref53","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/machines10030183"},{"key":"ref55","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross"},{"key":"ref56","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.2307\/2372560"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-007-9174-4"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610498.pdf?arnumber=10610498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:50:05Z","timestamp":1723269005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610498","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}