{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:13:47Z","timestamp":1777497227776,"version":"3.51.4"},"reference-count":50,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51809246"],"award-info":[{"award-number":["51809246"]}],"id":[{"id":"10.13039\/501100001809","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\/iros55552.2023.10341411","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"1683-1690","source":"Crossref","is-referenced-by-count":7,"title":["Model-based Adversarial Imitation Learning from Demonstrations and Human Reward"],"prefix":"10.1109","author":[{"given":"Jie","family":"Huang","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangshan","family":"Hao","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongshun","family":"Juan","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Randy","family":"Gomez","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan Co., Ltd,Wako,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Nakarnura","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan Co., Ltd,Wako,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangliang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","volume-title":"Mastering the real-time strategy game starcraft ii","author":"DeepMind","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref6","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Stochastic neural networks for hierarchical reinforcement learning","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Florensa"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref9","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proceedings of the 30th International Conference on Artificial Intelligence and Statistics","author":"Ross"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref12","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","volume":"1","author":"Ng"},{"key":"ref13","first-page":"2760","article-title":"Model-free imitation learning with policy optimization","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Ho"},{"key":"ref14","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9248"},{"key":"ref16","article-title":"Uncertainty-aware model-based reinforcement learning with application to autonomous driving","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Benchmarking model-based reinforcement learning","author":"Wang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTCC50638.2020.9259716"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2912447"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525837"},{"key":"ref22","article-title":"Towards principled methods for training generative adversarial networks","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Arjovsky"},{"key":"ref23","first-page":"5326","article-title":"Robust imitation of diverse behaviors","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS)","author":"Wang"},{"key":"ref24","article-title":"Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Peng"},{"key":"ref25","article-title":"Generative adversarial imitation from observation","author":"Torabi","year":"2018","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"390","article-title":"End-to-end differen-tiable adversarial imitation learning","volume-title":"International Conference on Machine Learning","author":"Baram"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref28","first-page":"195","article-title":"Uncertainty-driven imagination for continuous deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Kalweit"},{"key":"ref29","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"Feinberg","year":"2018","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Model-ensemble trust-region policy optimization","author":"Kurutach","year":"2018","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1538788.1538812"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225072"},{"key":"ref33","article-title":"Agnostic system identification for model-based reinforcement learning","author":"Ross","year":"2012","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197222"},{"key":"ref35","article-title":"Keypoints into the future: Self-supervised correspondence in model-based reinforcement learning","author":"Manuelli","year":"2020","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Model-based versus model-free deep reinforcement learning for autonomous racing cars","author":"Brunnbauer","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3065271"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"issue":"3-4","key":"ref40","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-Iearning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9283-7"},{"key":"ref43","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"MacGlashan"},{"key":"ref44","article-title":"Deep reinforcement learning from policy-dependent human feedback","author":"Arumugam","year":"2019","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Gan-based interactive reinforcement learning from demonstration and human evaluative feedback","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040156"},{"key":"ref47","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Schulman"},{"key":"ref48","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref50","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"}],"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\/10341411.pdf?arnumber=10341411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:31:21Z","timestamp":1769488281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341411","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}