{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T15:00:59Z","timestamp":1773241259722,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research (ONR)","doi-asserted-by":"publisher","award":["N00014-19-1-2076,N00014-22-1-2834,N00173-21-1-G009"],"award-info":[{"award-number":["N00014-19-1-2076,N00014-22-1-2834,N00173-21-1-G009"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2219755"],"award-info":[{"award-number":["CNS-2219755"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007187","name":"MIT Lincoln Laboratory","doi-asserted-by":"publisher","award":["7000437192"],"award-info":[{"award-number":["7000437192"]}],"id":[{"id":"10.13039\/100007187","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341378","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"3688-3695","source":"Crossref","is-referenced-by-count":6,"title":["Learning Models of Adversarial Agent Behavior Under Partial Observability"],"prefix":"10.1109","author":[{"given":"Sean","family":"Ye","sequence":"first","affiliation":[{"name":"Institute of Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manisha","family":"Natarajan","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohan","family":"Paleja","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Letian","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew C.","family":"Gombolay","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"WaveWatch III Wave Model, NOAA\/NCEP","year":"2023"},{"key":"ref2","volume-title":"World Drug Report 2022, by the United Nations Office on Drugs and Crime","year":"2023"},{"key":"ref3","first-page":"1262","article-title":"Learning from suboptimal demonstration via self-supervised reward regression","volume-title":"Conference on robot learning","author":"Chen"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00246"},{"key":"ref5","volume-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","author":"Chen","year":"2016"},{"key":"ref6","first-page":"28","article-title":"A recurrent latent variable model for sequential data","author":"Chung","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2007.916140"},{"key":"ref8","first-page":"1802","article-title":"Learning policy representations in multi agent systems","volume-title":"International conference on machine learning","author":"Grover"},{"key":"ref9","article-title":"Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets","volume":"30","author":"Hausman","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"International conference on machine learning","author":"He"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811776"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/iet-smt.2016.0044"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.533"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2008327"},{"key":"ref15","volume-title":"Infogail: Interpretable imitation learning from visual demonstrations","author":"Li","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12889"},{"key":"ref17","first-page":"6417","article-title":"Interpretable and personalized apprenticeship scheduling: Learning interpretable scheduling policies from heterogeneous user demonstrations","volume":"33","author":"Paleja","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Variational autoen-coders for opponent modeling in multi-agent systems","author":"Papoudakis","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"4257","article-title":"Modeling others using oneself in multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Raileanu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5815\/ijigsp.2013.06.08"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/taes.2003.1261132"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889616"},{"key":"ref23","article-title":"Learning when to communicate at scale in multi agent cooperative and compet-itive tasks","author":"Singh","year":"2018","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"9407","article-title":"Variational imitation learning with diverse-quality demonstrations","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Tangkaratt"},{"key":"ref25","first-page":"6818","article-title":"Imitation learning from imperfect demonstration","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.221"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341378.pdf?arnumber=10341378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:13:55Z","timestamp":1703031235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341378\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341378","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}