{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T23:12:39Z","timestamp":1773961959750,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["IEEE Trans. Games"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tg.2025.3628606","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:29Z","timestamp":1768255469000},"page":"173-184","source":"Crossref","is-referenced-by-count":0,"title":["Adapter-RL: Adaptation of Any Agent Using Reinforcement Learning"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8923-2562","authenticated-orcid":false,"given":"Yizhao","family":"Jin","sequence":"first","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4060-5226","authenticated-orcid":false,"given":"Gregory","family":"Slabaugh","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3180-7451","authenticated-orcid":false,"given":"Simon","family":"Lucas","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. fourteenth Int. Conf. Artif. Intell. statistics. JMLR Workshop Conf. Proc.","author":"Ross","year":"2011"},{"key":"ref2","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho","year":"2016"},{"key":"ref3","article-title":"Assessing generalization in deep reinforcement learning","author":"Packer","year":"2018"},{"key":"ref4","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau","year":"1988"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref7","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng","year":"2000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029475"},{"key":"ref11","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Rebuffi","year":"2017"},{"key":"ref12","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.840"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.626"},{"key":"ref16","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume":"34","author":"Mahabadi","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"ref18","article-title":"Tiny adapters for vision transformers","author":"Marouf","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref20","article-title":"LORA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref21","article-title":"Atlas: Adapter-based multi-modal continual learning with a two-stage learning strategy","author":"Li","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-8170-9_22"},{"key":"ref23","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"Nagabandi","year":"2018"},{"key":"ref24","article-title":"Towards deep symbolic reinforcement learning","author":"Garnelo","year":"2016"},{"key":"ref25","article-title":"Human-timescale adaptation in an open-ended task space","author":"Bauer","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-024-00845-w"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref28","article-title":"Mastering Chess and Shogi by self-play with a general reinforcement learning algorithm","author":"Silver","year":"2017"},{"key":"ref29","article-title":"Accelerating self-play learning in Go","author":"Wu","year":"2019"},{"key":"ref30","article-title":"Adversarial policies beat professional-level Go AIs","author":"Wang","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v9i1.12681"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v39i1.2777"},{"key":"ref33","article-title":"Measuring generalization of deep reinforcement learning applied to real-time strategy games","volume-title":"Proc. Assoc. Advance. Artif. Intell. 2021 Workshop Reinforcement Learn. Games","author":"Huang","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref36","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref37","first-page":"621","article-title":"Towards playing full Moba games with deep reinforcement learning","volume":"33","author":"Ye","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref38","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11442848\/11340763.pdf?arnumber=11340763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:09:22Z","timestamp":1773950962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11340763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2025.3628606","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}