{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:25:17Z","timestamp":1775665517477,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"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":[[2025,9,30]]},"DOI":"10.1109\/humanoids65713.2025.11203207","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:50Z","timestamp":1761326150000},"page":"981-988","source":"Crossref","is-referenced-by-count":2,"title":["Extremum Flow Matching for Offline Goal Conditioned Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Quentin","family":"Rouxel","sequence":"first","affiliation":[{"name":"Université de Lorraine,Inria, CNRS,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Clemente","family":"Donoso","sequence":"additional","affiliation":[{"name":"Université de Lorraine,Inria, CNRS,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Chen","sequence":"additional","affiliation":[{"name":"Université de Lorraine,Inria, CNRS,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serena","family":"Ivaldi","sequence":"additional","affiliation":[{"name":"Université de Lorraine,Inria, CNRS,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Baptiste","family":"Mouret","sequence":"additional","affiliation":[{"name":"Université de Lorraine,Inria, CNRS,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref3","article-title":"Goal-conditioned imitation learning","author":"Ding","year":"2019","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.028"},{"key":"ref5","article-title":"From play to policy: Conditional behavior generation from uncurated robot data","author":"Cui","year":"2023","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.121"},{"key":"ref8","article-title":"Ai robots and humanoid ai: Review, perspectives and directions","author":"Cao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.124140"},{"key":"ref10","article-title":"Learning latent plans from play","author":"Lynch","year":"2020","journal-title":"CoRL"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref12","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023","journal-title":"CoRL"},{"key":"ref13","article-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2023","journal-title":"ICLR"},{"key":"ref14","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021","journal-title":"ICLR"},{"key":"ref15","article-title":"Enhancing decision transformer with diffusion-based trajectory branch generation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Hiql: Offline goal-conditioned rl with latent states as actions","author":"Park","year":"2023","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29215"},{"key":"ref18","article-title":"What makes a good diffusion planner for decision making?","author":"Lu","year":"2025","journal-title":"ICLR"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref21","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref22","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"ICML","author":"Janner","year":"2022"},{"key":"ref23","article-title":"Generative skill chaining: Long-horizon skill planning with diffusion models","author":"Mishra","year":"2023","journal-title":"CoRL"},{"key":"ref24","article-title":"Simple hierarchical planning with diffusion","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref25","article-title":"Generative trajectory stitching through diffusion composition","author":"Luo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Stochastic interpolants: A unifying framework for flows and diffusions","author":"Albergo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Building normalizing flows with stochastic interpolants","author":"Albergo","year":"2023","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769838"},{"key":"ref29","article-title":"Adaflow: Imitation learning with variance-adaptive flow-based policies","author":"Hu","year":"2024","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801521"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i14.33617"},{"key":"ref32","article-title":"Energy-weighted flow matching for offline reinforcement learning","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Flow q-learning","author":"Park","year":"2025","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/1911031"},{"key":"ref35","article-title":"Diffusion world model: Future modeling beyond step-by-step rollout for offline reinforcement learning","author":"Ding","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Learning from reward-free offline data: A case for planning with latent dynamics models","author":"Sobal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Double q-learning","author":"Hasselt","year":"2010","journal-title":"NeurIPS"},{"key":"ref38","article-title":"Ogbench: Benchmarking offline goal-conditioned rl","author":"Park","year":"2025","journal-title":"ICLR"},{"key":"ref39","article-title":"Learning to reach goals via iterated supervised learning","author":"Ghosh","year":"2021","journal-title":"ICLR"},{"key":"ref40","article-title":"Optimal goal-reaching reinforcement learning via quasimetric learning","author":"Wang","year":"2023","journal-title":"ICML"},{"key":"ref41","article-title":"Contrastive learning as goal-conditioned reinforcement learning","author":"Eysenbach","year":"2022","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396094"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3152844"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/mra.2023.3270222"}],"event":{"name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2025,9,30]]},"end":{"date-parts":[[2025,10,2]]}},"container-title":["2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11202977\/11203009\/11203207.pdf?arnumber=11203207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:48:57Z","timestamp":1761367737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11203207\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/humanoids65713.2025.11203207","relation":{},"subject":[],"published":{"date-parts":[[2025,9,30]]}}}