{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:40:06Z","timestamp":1735198806608,"version":"3.32.0"},"reference-count":66,"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\/iros58592.2024.10802085","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"7461-7468","source":"Crossref","is-referenced-by-count":0,"title":["Off-dynamics Conditional Diffusion Planners"],"prefix":"10.1109","author":[{"given":"Wen Zheng","family":"Terence Ng","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianda","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","year":"2020","author":"Levine","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"journal-title":"Abbas, Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments.","article-title":"Leveraging optimal transport for enhanced offline reinforcement learning in surgical robotic environments","author":"Zare","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3351797"},{"key":"ref5","first-page":"24753","article-title":"Neorl: A near real-world benchmark for offline reinforcement learning","volume":"35","author":"Qin","year":"2022","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3324458"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12625"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1831925"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2018-9249"},{"article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Conference on Robot Learning","author":"Mandlekar","key":"ref12"},{"key":"ref13","article-title":"Dara: Dynamics-aware reward augmentation in offline reinforcement learning","author":"Liu","year":"2021","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"issue":"1","key":"ref16","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-5004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2017.09.110"},{"key":"ref19","article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","author":"Eysenbach","year":"2020","journal-title":"ICLR"},{"key":"ref20","first-page":"23230","article-title":"Mismatched no more: Joint model-policy optimization for model-based rl","volume":"35","author":"Eysenbach","year":"2022","journal-title":"NeurIPS"},{"key":"ref21","first-page":"36599","article-title":"When to trust your simulator: Dynamics-aware hybrid offline-and-online reinforcement learning","volume":"35","author":"Niu","year":"2022","journal-title":"NeurIPS"},{"key":"ref22","first-page":"28784","article-title":"Unsupervised domain adaptation with dynamics-aware rewards in reinforcement learning","volume":"34","author":"Liu","year":"2021","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11044"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341149"},{"article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","year":"2016","author":"Christiano","key":"ref25"},{"key":"ref26","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref27","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref29","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","year":"2021","author":"Nichol","key":"ref30"},{"article-title":"Diffwave: A versatile diffusion model for audio synthesis","year":"2020","author":"Kong","key":"ref31"},{"article-title":"Video diffusion models","year":"2022","author":"Ho","key":"ref32"},{"key":"ref33","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"ICML"},{"key":"ref34","article-title":"Is conditional generative modeling all you need for decision making?","author":"Ajay","year":"2023","journal-title":"The Eleventh ICLR"},{"article-title":"Instructed diffuser with temporal condition guidance for offline reinforcement learning","year":"2023","author":"Hu","key":"ref35"},{"key":"ref36","article-title":"Classifier-free diffusion guidance","volume":"abs\/2207.12598","author":"Ho","year":"2022"},{"article-title":"Off-dynamics inverse reinforcement learning from hetero-domain","year":"2021","author":"Kang","key":"ref37"},{"key":"ref38","first-page":"3917","article-title":"An imitation from observation approach to transfer learning with dynamics mismatch","volume":"33","author":"Desai","year":"2020","journal-title":"NeurIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561731"},{"key":"ref40","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"NeurIPS"},{"key":"ref41","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref42","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref43","first-page":"8599","article-title":"Gradtts: A diffusion probabilistic model for text-to-speech","volume-title":"ICML.","author":"Popov","year":"2021"},{"key":"ref44","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"ICML.","author":"Arjovsky","year":"2017"},{"key":"ref45","article-title":"Improved training of wasserstein gans","volume":"30","author":"Gulrajani","year":"2017","journal-title":"NeurIPS"},{"key":"ref46","first-page":"2249","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref49","article-title":"Geodiff: A geometric diffusion model for molecular conformation generation","author":"Xu","year":"2021","journal-title":"ICLR"},{"key":"ref50","article-title":"A conditional point diffusion-refinement paradigm for 3d point cloud completion","author":"Lyu","year":"2021","journal-title":"ICLR"},{"key":"ref51","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"article-title":"Madiff: Offline multi-agent learning with diffusion models","year":"2023","author":"Zhu","key":"ref52"},{"article-title":"Metadiffuser: Diffusion model as conditional planner for offline metarl","year":"2023","author":"Ni","key":"ref53"},{"article-title":"Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning","year":"2023","author":"He","key":"ref54"},{"article-title":"Safe offline reinforcement learning with feasibility-guided diffusion model","year":"2024","author":"Zheng","key":"ref55"},{"article-title":"Diffuserlite: Towards real-time diffusion planning","year":"2024","author":"Dong","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"volume-title":"Reinforcement learning: An introduction.","year":"2018","author":"Sutton","key":"ref58"},{"article-title":"D4rl: Datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref59"},{"key":"ref60","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"ICML.","author":"Fujimoto","year":"2019"},{"key":"ref61","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"NeurIPS"},{"key":"ref62","first-page":"1179","article-title":"Conservative qlearning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"NeurIPS"},{"key":"ref63","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021","journal-title":"ICLR"},{"key":"ref64","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"NeurIPS"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref66","article-title":"Adaptdiffuser: Diffusion models as adaptive self-evolving planners","author":"Liang","year":"2023","journal-title":"ICML"}],"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\/10802085.pdf?arnumber=10802085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:59:32Z","timestamp":1735196372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802085","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}