{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:41:07Z","timestamp":1771612867327,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Lingfeng Sun was interning at Horizon Robotics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/lra.2023.3284660","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T17:27:54Z","timestamp":1686331674000},"page":"4569-4576","source":"Crossref","is-referenced-by-count":7,"title":["Efficient Multi-Task and Transfer Reinforcement Learning With Parameter-Compositional Framework"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1134-4103","authenticated-orcid":false,"given":"Lingfeng","family":"Sun","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, University of California, Berkeley, Albany, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3276-3390","authenticated-orcid":false,"given":"Haichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Horizon Robotics, Cupertino, CA, USA"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"Horizon Robotics, Cupertino, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-6639","authenticated-orcid":false,"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of California, Berkeley, Albany, CA, USA"}]}],"member":"263","reference":[{"key":"ref13","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","author":"sodhani","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","article-title":"A simple approach for general task-oriented picking using placing constraints","author":"wang","year":"2023"},{"key":"ref12","first-page":"4499","article-title":"Distral: Robust multitask reinforcement learning","author":"teh","year":"0","journal-title":"Proc 31st Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561954"},{"key":"ref15","first-page":"1","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","article-title":"MT-Opt: Continuous multi-task robotic reinforcement learning at scale","author":"kalashnikov","year":"2021"},{"key":"ref31","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref11","first-page":"1","article-title":"Sharing knowledge in multi-task deep reinforcement learning","author":"d'eramo","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref10","first-page":"5824","article-title":"Gradient surgery for multi-task learning","author":"yu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"ester","year":"0","journal-title":"Proc Int Conf Knowl Discov Data Mining"},{"key":"ref2","first-page":"1","article-title":"panda-gym: Open-source goal-conditioned environments for robotic learning","author":"gallou\u00e9dec","year":"0","journal-title":"Proc 4th Robot Learn Workshop Self-Supervised Lifelong Learn NeurIPS"},{"key":"ref1","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018"},{"key":"ref17","first-page":"1","article-title":"Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning","author":"julian","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.9"},{"key":"ref24","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref23","article-title":"A simple approach to continual learning by transferring skill parameters","author":"zentner","year":"2021"},{"key":"ref26","first-page":"1","article-title":"Successor features for transfer in reinforcement learning","author":"barreto","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","first-page":"2661","article-title":"Zero-shot task generalization with multi-task deep reinforcement learning","author":"oh","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref20","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref22","article-title":"Coverage as a principle for discovering transferable behavior in reinforcement learning","author":"campos","year":"2021"},{"key":"ref21","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref28","first-page":"1","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","article-title":"Universal successor features for transfer reinforcement learning","author":"ma","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811697"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3233\/IA-150080"},{"key":"ref7","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","first-page":"166","article-title":"Modular multitask reinforcement learning with policy sketches","author":"andreas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","first-page":"10991","article-title":"Bridging multi-task learning and meta-learning: Towards efficient training and effective adaptation","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref6","first-page":"21495","article-title":"PaCo: Parameter-compositional multi-task reinforcement learning","author":"sun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1","article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of MAML","author":"raghu","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10153452\/10147360.pdf?arnumber=10147360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T19:43:08Z","timestamp":1689018188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10147360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":35,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3284660","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}