{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:14:21Z","timestamp":1777497261704,"version":"3.51.4"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160939","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"4991-4998","source":"Crossref","is-referenced-by-count":6,"title":["GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback"],"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":"Nakamura","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":"10.1038\/nature14236"},{"key":"ref2","author":"DeepMind","year":"2019","journal-title":"Mastering the real-time strategy game starcraft ii"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref5","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Stochastic neural networks for hierarchical reinforcement learning","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Florensa"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref9","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Riedmiller"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525837"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2022.3144956"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0018720816644364"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2020.3019151"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2020.3017781"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211041652"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3116119"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref20","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Ng"},{"key":"ref21","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":"ref22","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9248"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2912447"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref28","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Ziebart"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390286"},{"key":"ref30","first-page":"1449","article-title":"A game-theoretic approach to apprenticeship learning","author":"Syed","year":"2008","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9121-3"},{"key":"ref32","article-title":"Towards principled methods for training generative adversarial networks","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Arjovsky"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref35","article-title":"Reinforcement learning from imperfect demonstrations","volume-title":"Proceedings of International Conference on Learning Representations (ICLR) Workshop","author":"Gao"},{"key":"ref36","article-title":"Sqil: Imitation learning via reinforcement learning with sparse rewards","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Reddy"},{"key":"ref37","first-page":"43","article-title":"When humans arent optimal: Robots that collaborate with risk-aware humans","volume-title":"2020 15th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)","author":"Kwon"},{"key":"ref38","first-page":"6818","article-title":"Imitation learning from imperfect demonstration","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5953"},{"key":"ref40","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Ng"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref44","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":"ref45","article-title":"Deep reinforcement learning from policy-dependent human feedback","author":"Arumugam","year":"2019","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"8011","article-title":"Reward learning from human preferences and demonstrations in atari","author":"Ibarz","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"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":"Playing atari with deep reinforcement learning","volume-title":"Proceedings of Deep Learning Workshop at International Conference on Neural Information Processing Systems (NIPS)","author":"Mnih"},{"key":"ref49","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Fujimoto"},{"key":"ref50","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160939.pdf?arnumber=10160939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T11:42:50Z","timestamp":1709293370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160939","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}