{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:09:51Z","timestamp":1774631391161,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246167","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"11639-11645","source":"Crossref","is-referenced-by-count":1,"title":["Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations"],"prefix":"10.1109","author":[{"given":"Haitong","family":"Ma","sequence":"first","affiliation":[{"name":"Harvard University,School of Engineering and Applied Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Dai","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,School of Computational Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaolin","family":"Ren","sequence":"additional","affiliation":[{"name":"Harvard University,School of Engineering and Applied Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yebin","family":"Wang","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Li","sequence":"additional","affiliation":[{"name":"Harvard University,School of Engineering and Applied Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref2","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2007.4813899"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref5","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross"},{"key":"ref7","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Imitation learning via off-policy distribution matching","author":"Kostrikov","year":"2019"},{"key":"ref9","article-title":"Dualdice: Behavior-agnostic estimation of discounted stationary distribution corrections","volume":"32","author":"Nachum","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Demodice: Offline imitation learning with supplementary imperfect demonstrations","volume-title":"International Conference on Learning Representations","author":"Kim"},{"key":"ref11","first-page":"14 639","article-title":"Versatile offline imitation from observations and examples via regularized state-occupancy matching","volume-title":"International Conference on Machine Learning","author":"Ma"},{"key":"ref12","article-title":"Behavioral cloning from noisy demonstrations","volume-title":"International Conference on Learning Representations","author":"Sasaki"},{"key":"ref13","article-title":"Reinforcement learning via fenchel-rockafellar duality","author":"Nachum","year":"2020"},{"key":"ref14","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"International conference on machine learning","author":"Arjovsky"},{"issue":"2","key":"ref15","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng","year":"2000","journal-title":"Icml"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref17","article-title":"A game-theoretic approach to apprenticeship learning","volume":"20","author":"Syed","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"24 725","article-title":"Discriminator-weighted offline imitation learning from suboptimal demonstrations","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref19","first-page":"1259","article-title":"A divergence minimization perspective on imitation learning methods","volume-title":"Conference on robot learning","author":"Ghasemipour"},{"key":"ref20","first-page":"8252","article-title":"Lobsdice: Offline learning from observation via stationary distribution correction estimation","volume":"35","author":"Kim","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref22","article-title":"Successor Features for Transfer in Reinforcement Learning","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Barreto","year":"2017"},{"key":"ref23","article-title":"Trail: Near-optimal imitation learning with suboptimal data","author":"Yang","year":"2021"},{"key":"ref24","article-title":"Opal: Offline primitive discovery for accelerating offline reinforcement learning","author":"Ajay","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/21m1401243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref27","first-page":"20 095","article-title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Agarwal","year":"2020"},{"key":"ref28","first-page":"26 447","article-title":"Making linear mdps practical via contrastive representation learning","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref29","article-title":"Spectral decomposition representation for reinforcement learning","author":"Ren","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801637"},{"issue":"2","key":"ref31","article-title":"Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics","volume":"13","author":"Gutmann","year":"2012","journal-title":"Journal of machine learning research"},{"key":"ref32","article-title":"Offline imitation learning upon sub-optimal demonstrations by primal-dual representation","author":"Ma"},{"key":"ref33","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383842"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1953-0052691-0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref37","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246167.pdf?arnumber=11246167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:10:09Z","timestamp":1765519809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246167","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}