{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:56Z","timestamp":1774420136074,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890371","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["GIST: Guided Interpretable Large Language Model Strategy Transfer for Multi-Task Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Bo","family":"Zhao","sequence":"first","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Tang","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"Parisotto","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref6","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref8","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref10","first-page":"4548","article-title":"Overcoming catastrophic forgetting with hard attention to the task","volume-title":"International Conference on Machine Learning","author":"Serra"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"ref12","article-title":"Pathnet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref14","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"International Conference on Machine Learning","author":"Zenke"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref16","first-page":"4528","article-title":"Progress & compress: A scalable framework for continual learning","volume-title":"International conference on machine learning","author":"Schwarz"},{"key":"ref17","article-title":"Kan: Kolmogorov-arnold networks","author":"Liu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01742-1_5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007327622663"},{"key":"ref20","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref21","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref22","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"International Conference on Machine Learning","author":"Duan"},{"key":"ref23","article-title":"Distral: Robust multi-task reinforcement learning","volume":"30","author":"Teh","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Openai gym","author":"Brockman","year":"2016"},{"issue":"140","key":"ref25","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974508"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890371.pdf?arnumber=10890371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:37Z","timestamp":1774416397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890371","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}