{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:32:46Z","timestamp":1759332766874,"version":"3.32.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802715","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"611-618","source":"Crossref","is-referenced-by-count":1,"title":["Towards Accurate And Robust Dynamics and Reward Modeling for Model-Based Offline Inverse Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Gengyu","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Illinois,Department of Computer Science,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Illinois,Department of Computer Science,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1145\/1015330.1015430"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/j.artint.2021.103500"},{"volume-title":"CoRL","author":"Das","article-title":"Model-based inverse reinforcement learning from visual demonstrations","key":"ref3"},{"volume-title":"NeurIPS","author":"Du","article-title":"Implicit generation and modeling with energy based models","key":"ref4"},{"year":"2020","author":"Fu","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1002\/9781119387596"},{"volume-title":"ICML","author":"Haarnoja","article-title":"Reinforcement learning with deep energy-based policies","key":"ref7"},{"volume-title":"ICML","author":"Haarnoja","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","key":"ref8"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1007\/s10543-008-0164-1"},{"volume-title":"NeurIPS","author":"Ho","article-title":"Denoising diffusion probabilistic models","key":"ref10"},{"volume-title":"NeurIPS","author":"Hoffman","article-title":"Elbo surgery: yet another way to carve up the variational evidence lower bound","key":"ref11"},{"volume-title":"NeurIPS","author":"Karras","article-title":"Elucidating the design space of diffusion-based generative models","key":"ref12"},{"volume-title":"NeurIPS","author":"Kidambi","article-title":"Morel: Model-based offline reinforcement learning","key":"ref13"},{"volume-title":"ICLR","author":"Kingma","article-title":"Auto-encoding variational bayes","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1056\/NEJMoa1210384"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.5555\/3295222.3295387"},{"volume-title":"ICML","author":"Ng","article-title":"Algorithms for inverse reinforcement learning","key":"ref17"},{"volume-title":"COLT","author":"Russell","article-title":"Learning agents for uncertain environments","key":"ref18"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.23919\/ACC45564.2020.9147344"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1016\/j.automatica.2022.110242"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CDC42340.2020.9303883"},{"volume-title":"IJICC","author":"Shao","article-title":"A survey of inverse reinforcement learning techniques","key":"ref22"},{"volume-title":"ICML","author":"Sohl-Dickstein","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","key":"ref23"},{"volume-title":"NeurIPS","author":"Song","article-title":"Generative modeling by estimating gradients of the data distribution","key":"ref24"},{"volume-title":"UAI","author":"Song","article-title":"Score matching: a scalable approach to density and score estimation","key":"ref25"},{"volume-title":"ICLR","author":"Song","article-title":"Score-based generative modeling through stochastic differential equations","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/IROS.2012.6386109"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1162\/NECO_a_00142"},{"volume-title":"ICML","author":"Welling","article-title":"Bayesian learning via stochastic gradient langevin dynamics","key":"ref29"},{"volume-title":"NeurIPS","author":"Yu","article-title":"Combo: Conservative offline model-based policy optimization","key":"ref30"},{"volume-title":"NeurIPS","author":"Yu","article-title":"Mopo: Model-based offline policy optimization","key":"ref31"},{"volume-title":"ICLR","author":"Yue","article-title":"CLARE: Conservative model-based reward learning for offline inverse reinforcement learning","key":"ref32"},{"volume-title":"NeurIPS","author":"Zeng","article-title":"When demonstrations meet generative world models: a maximum likelihood framework for offline inverse reinforcement learning","key":"ref33"},{"volume-title":"AAAI","author":"Ziebart","article-title":"Maximum entropy inverse reinforcement learning","key":"ref34"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802715.pdf?arnumber=10802715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:01:58Z","timestamp":1735196518000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802715","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}