{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:40:06Z","timestamp":1757608806254,"version":"3.44.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127641","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"10854-10860","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Feng","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore,Department of Computer Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Luan","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore,Department of Computer Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin Yuchen","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore,Department of Computer Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harold","family":"Soh","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore,Department of Computer Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00071-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570410"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3443501"},{"key":"ref4","first-page":"20035","article-title":"Hierarchical diffusion for offline decision making","volume-title":"Int. Conf. Mach. Learn., ser. Proceedings of Machine Learning Research","volume":"202","author":"Li","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01712"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1977.32"},{"volume-title":"Principles of Model Checking","year":"2008","author":"Baier","key":"ref7"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-50763-7","volume-title":"Formal Methods for DiscreteTime Dynamical Systems","volume":"89","author":"Belta","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942756"},{"key":"ref10","first-page":"1587","article-title":"Optimal policy generation for partially satisfiable co-safe LTL specifications","volume-title":"Int. Joint Conf. Artif. Intell.","volume":"15","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011254632723"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v28i1.13908"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref17","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Int. Conf. Mach. Learn.","volume":"162","author":"Janner","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref19","first-page":"68406851","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Inf. Process. Syst."},{"key":"ref20","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref21","first-page":"452","article-title":"Teaching multiple tasks to an RL agent using LTL","volume-title":"Proc. Int. Conf. Autonomous Agents Multiagent Syst.","author":"Toro Icarte","year":"2018"},{"key":"ref22","first-page":"10497","article-title":"LTL2Action: Generalizing LTL instructions for multi-task RL","volume-title":"Int. Conf. Mach. Learn.","author":"Vaezipoor","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561952"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref27","first-page":"20","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Int. Conf. Mach. Learn., ser. Proceedings of Machine Learning Research","volume":"48","author":"Mnih"},{"key":"ref28","article-title":"Double q-learning","volume-title":"Advances in Neural Inf. Process. Syst.","volume":"23","author":"Hasselt","year":"2010"},{"key":"ref29","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Int. Conf. Mach. Learn., ser. Proceedings of Machine Learning Research","volume":"80","author":"Fujimoto","year":"2018"},{"journal-title":"Qlearning for continuous actions with cross-entropy guided policies","year":"2019","author":"Simmons-Edler","key":"ref30"},{"key":"ref31","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Int. Conf. Learn. Representations","author":"Chung","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.tm11181"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/2200000044"},{"key":"ref34","first-page":"32483","article-title":"Loss-guided diffusion models for plug-and-play controllable generation","volume-title":"Int. Conf. Mach. Learn.","volume":"202","author":"Song","year":"2023"},{"key":"ref35","first-page":"342","article-title":"Planning with temporally extended goals using heuristic search","volume-title":"Proc. Int. Conf. Automated Planning and Scheduling","author":"Baier","year":"2006"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/507"},{"key":"ref37","first-page":"17690","article-title":"Policy optimization with linear temporal logic constraints","author":"Voloshin","year":"2022","journal-title":"Advances in Neural Inf. Process. Syst."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104351"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5399536"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611432"},{"key":"ref41","article-title":"Temporal logic imitation: Learning plan-satisficing motion policies from demonstrations","volume-title":"6th Annual Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref42","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127641.pdf?arnumber=11127641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:45:49Z","timestamp":1756881949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127641","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}