{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:15:20Z","timestamp":1771924520196,"version":"3.50.1"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":[[2025,12,3]]},"DOI":"10.1109\/robio66223.2025.11378100","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:43:52Z","timestamp":1771879432000},"page":"2268-2273","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning with Stage-Wise Model Fusion for Sequential Object Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Yuhan","family":"Huang","sequence":"first","affiliation":[{"name":"School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Ning","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Hei","sequence":"additional","affiliation":[{"name":"School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10030105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO64047.2024.10907454"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72359-9_22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551399"},{"key":"ref5","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref8","first-page":"3540","article-title":"FeUdal networks for hierarchical reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Vezhnevets"},{"key":"ref9","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"Nachum","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126620"},{"key":"ref11","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Proceedings of the Conference on Robot Learning","author":"Gupta"},{"key":"ref12","first-page":"2016","author":"Coumans","journal-title":"Pybullet: a python module for physics simulation for games, robotics and machine learning"},{"issue":"268","key":"ref13","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Chengdu, China","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,7]]}},"container-title":["2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373909\/11375854\/11378100.pdf?arnumber=11378100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:23:05Z","timestamp":1771921385000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11378100\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/robio66223.2025.11378100","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}