{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:12:19Z","timestamp":1783527139198,"version":"3.55.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004787","name":"Hong Kong Research Grant Council through General Research Fund","doi-asserted-by":"publisher","award":["11218621"],"award-info":[{"award-number":["11218621"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100003012","name":"Research Impact Fund (RIF) Project","doi-asserted-by":"publisher","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}],"id":[{"id":"10.13039\/100003012","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3385570","type":"journal-article","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T15:43:16Z","timestamp":1714491796000},"page":"6843-6857","source":"Crossref","is-referenced-by-count":12,"title":["Policy Correction and State-Conditioned Action Evaluation for Few-Shot Lifelong Deep Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4857-5439","authenticated-orcid":false,"given":"Meng","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8563-148X","authenticated-orcid":false,"given":"Xinhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-1482","authenticated-orcid":false,"given":"Jianping","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Policy consolidation for continual reinforcement learning","author":"Kaplanis","year":"2019","journal-title":"arXiv:1902.00255"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"ref3","first-page":"16","article-title":"Experience replay for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rolnick"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412614"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3170485"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3280085"},{"key":"ref7","article-title":"Modular lifelong reinforcement learning via neural composition","author":"Mendez","year":"2022","journal-title":"arXiv:2207.00429"},{"key":"ref8","first-page":"1","article-title":"Generalisation in lifelong reinforcement learning through logical composition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tasse"},{"key":"ref9","article-title":"Skill-based meta-reinforcement learning","author":"Nam","year":"2022","journal-title":"arXiv:2204.11828"},{"key":"ref10","first-page":"3518","article-title":"A deep reinforcement learning approach to marginalized importance sampling with the successor representation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3412841.3441953"},{"key":"ref13","article-title":"Understanding domain randomization for sim-to-real transfer","author":"Chen","year":"2021","journal-title":"arXiv:2110.03239"},{"key":"ref14","article-title":"On the effectiveness of fine-tuning versus meta-reinforcement learning","author":"Mandi","year":"2022","journal-title":"arXiv:2206.03271"},{"issue":"13","key":"ref15","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"James","year":"2017","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref17","article-title":"Remember and forget experience replay for multi-agent reinforcement learning","author":"Weber","year":"2022","journal-title":"arXiv:2203.13319"},{"key":"ref18","article-title":"Gradient episodic memory with a soft constraint for continual learning","author":"Hu","year":"2020","journal-title":"arXiv:2011.07801"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17866-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113420"},{"key":"ref22","first-page":"28955","article-title":"Reincarnating reinforcement learning: Reusing prior computation to accelerate progress","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Agarwal"},{"key":"ref23","article-title":"Non-exemplar online class-incremental continual learning via dual-prototype self-augment and refinement","author":"Huo","year":"2023","journal-title":"arXiv:2303.10891"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"},{"key":"ref25","first-page":"6334","article-title":"Provable lifelong learning of representations","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Cao"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.neunet.2022.02.027","article-title":"Lifelong 3D object recognition and grasp synthesis using dual memory recurrent self-organization networks","volume":"150","author":"Santhakumar","year":"2022","journal-title":"Neural Netw."},{"issue":"3","key":"ref27","first-page":"2337","article-title":"Few-shot lifelong learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"35","author":"Mazumder"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref29","article-title":"Continual learning with hypernetworks","author":"von Oswald","year":"2019","journal-title":"arXiv:1906.00695"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00191"},{"key":"ref31","first-page":"476","article-title":"Hypernets and their application to learning spatial transformations","volume-title":"Proc. 27th Int. Conf. Artif. Neural Netw. Artif. Neural Netw. Mach. Learn. (ICANN)","volume":"27","author":"Potapov"},{"key":"ref32","first-page":"1","article-title":"Dynamic filter networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Jia"},{"key":"ref33","article-title":"SMASH: One-shot model architecture search through HyperNetworks","author":"Brock","year":"2017","journal-title":"arXiv:1708.05344"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26146"},{"key":"ref35","first-page":"9301","article-title":"Recomposing the reinforcement learning building blocks with hypernetworks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sarafian"},{"key":"ref36","first-page":"32438","article-title":"Rethinking individual global max in cooperative multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hong"},{"key":"ref37","article-title":"Replay-enhanced continual reinforcement learning","author":"Zhang","year":"2023","journal-title":"arXiv:2311.11557"},{"key":"ref38","first-page":"1","article-title":"Building a subspace of policies for scalable continual learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gaya"},{"key":"ref39","article-title":"Dynamic sparse training for deep reinforcement learning","author":"Sokar","year":"2021","journal-title":"arXiv:2106.04217"},{"key":"ref40","first-page":"1","article-title":"RLx2: Training a sparse deep reinforcement learning model from scratch","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tan"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3569096"},{"key":"ref42","first-page":"3692","article-title":"Smoothed action value functions for learning Gaussian policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nachum"},{"key":"ref43","first-page":"1365","article-title":"Regularized softmax deep multi-agent Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Pan"},{"key":"ref44","article-title":"Softmax Q-distribution estimation for structured prediction: A theoretical interpretation for RAML","author":"Ma","year":"2017","journal-title":"arXiv:1705.07136"},{"key":"ref45","first-page":"5916","article-title":"Revisiting the softmax Bellman operator: New benefits and new perspective","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref46","first-page":"3107","article-title":"Softmax policy gradient methods can take exponential time to converge","volume-title":"Proc. Conf. Learn. Theory","author":"Li"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10723-023-09663-0"},{"key":"ref49","first-page":"17662","article-title":"Online meta-critic learning for off-policy actor-critic methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhou"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904358"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109448"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3623405"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3579829"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3639371"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10510602.pdf?arnumber=10510602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:38:56Z","timestamp":1764959936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10510602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":54,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3385570","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}