{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:53:18Z","timestamp":1784904798207,"version":"3.55.0"},"reference-count":43,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160374","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"5902-5908","source":"Crossref","is-referenced-by-count":7,"title":["Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control"],"prefix":"10.1109","author":[{"given":"Jiayu","family":"Chen","sequence":"first","affiliation":[{"name":"School of Industrial Engineering, Purdue University,West Lafayette,IN,USA,47907"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Lan","sequence":"additional","affiliation":[{"name":"George Washington University,Department of Electrical and Computer Engineering,Washington D.C.,USA,20052"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaneet","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"KAUST,CS Department,Thuwal,Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"80","article-title":"Augmenting gail with be for sample efficient imitation learning","author":"jena","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref35","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref12","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","volume":"abs 1710 11248","author":"fu","year":"2017","journal-title":"CoRR"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref15","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proceedings of the 2nd International Conference on Learning Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907421"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560907"},{"key":"ref36","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","volume":"78","author":"finn","year":"0","journal-title":"Proceedings of the 1st Annual Conference on Robot Learning"},{"key":"ref31","author":"cover","year":"1999","journal-title":"Elements of Information Theory"},{"key":"ref30","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1986.1165342"},{"key":"ref10","first-page":"303","article-title":"Causality, feedback and directed information","author":"massey","year":"0","journal-title":"Proc Int Symp Inf Theory Applic (ISITA-90)"},{"key":"ref32","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref39","first-page":"15486","article-title":"Stacked capsule autoencoders","author":"kosiorek","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/79.543975"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5580-x"},{"key":"ref23","first-page":"3418","article-title":"Compile: Compositional imitation learning and execution","volume":"97","author":"kipf","year":"0","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007469218079"},{"key":"ref25","first-page":"883","article-title":"Provable hierarchical imitation learning via EM","volume":"130","author":"zhang","year":"0","journal-title":"Proceedings of The 24th International Conference on Artificial Intelligence and Statistics"},{"key":"ref20","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"0","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF02418571"},{"key":"ref41","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","volume":"28","author":"chung","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"2923","article-title":"Hierarchical imitation and reinforcement learning","volume":"80","author":"le","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref21","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume":"15","author":"ross","year":"0","journal-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics"},{"key":"ref43","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"bottou","year":"0","journal-title":"Proceedings of the 19th International Conference on Computational Statistics"},{"key":"ref28","first-page":"2010","article-title":"DAC: the double actor-critic architecture for learning options","volume":"32","author":"zhang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"0","journal-title":"Proceedings of the 33rd AAAI Conference on Artificial Intelligence"},{"key":"ref29","article-title":"The skill-action architecture: Learning abstract action embeddings for reinforcement learning","author":"li","year":"0","journal-title":"Submissions of the 9th International Conference on Learning Representations"},{"key":"ref8","first-page":"5097","article-title":"Ad-versarial option-aware hierarchical imitation learning","author":"jing","year":"0","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"ref7","article-title":"Directed-info GAIL: learning hierarchical policies from unsegmented demon-strations using directed information","author":"sharma","year":"0","journal-title":"Proceedings of the 7th International Conference on Learning Representations"},{"key":"ref9","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"ebert","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Playing atari games with deep reinforcement learning and human checkpoint replay","volume":"abs 1607 5077","author":"hosu","year":"2016","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref40","article-title":"Three tutorial lectures on entropy and counting","author":"galvin","year":"2014","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\/10160374.pdf?arnumber=10160374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:37:38Z","timestamp":1690220258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160374","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}