{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:19:19Z","timestamp":1768313959954,"version":"3.49.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"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":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312643","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"6150-6155","source":"Crossref","is-referenced-by-count":0,"title":["Model Selection for Inverse Reinforcement Learning via Structural Risk Minimization"],"prefix":"10.1109","author":[{"given":"Chendi","family":"Qu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China"}]},{"given":"Jianping","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China"}]},{"given":"Xiaoming","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China"}]},{"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,The State Key Laboratory of Industrial Control Technology,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139555"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9451-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-016-9556-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461076"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10108-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref10","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume":"7","author":"Ramachandran","year":"2007","journal-title":"IJCAI"},{"key":"ref11","article-title":"Modeling interaction via the principle of maximum causal entropy","author":"Ziebart","year":"2010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10313"},{"key":"ref13","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"29 663","article-title":"Dynamic inverse reinforcement learning for characterizing animal behavior","volume":"35","author":"Ashwood","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Automated feature selection for inverse reinforcement learning","author":"Baimukashev","year":"2024"},{"key":"ref16","article-title":"Teaching inverse reinforcement learners via features and demonstrations","volume":"31","author":"Haug","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Aaai","volume":"8","author":"Ziebart","year":"2008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/18.930926"},{"key":"ref19","article-title":"Foundations of machine learning","author":"Mohri","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304229"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/ACC60939.2024.10644471"},{"key":"ref22","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44581-1_15"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312643.pdf?arnumber=11312643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:05:38Z","timestamp":1768295138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312643","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}