{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T02:50:08Z","timestamp":1781232608175,"version":"3.54.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Innovation 2030-Key Project","award":["2021ZD0201404"],"award-info":[{"award-number":["2021ZD0201404"]}]},{"name":"Tencent Rhino-Bird Research Elite Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tnnls.2023.3280085","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T17:35:43Z","timestamp":1686159343000},"page":"14588-14602","source":"Crossref","is-referenced-by-count":10,"title":["Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0204-4758","authenticated-orcid":false,"given":"Tiantian","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxing","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1754-1837","authenticated-orcid":false,"given":"Deheng","family":"Ye","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Fu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3542-0593","authenticated-orcid":false,"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7163-345X","authenticated-orcid":false,"given":"Bin","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2169-0007","authenticated-orcid":false,"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Research Institute of Tsinghua University in Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref3","volume-title":"On-Line Q-Learning Using Connectionist Systems","author":"Rummery","year":"1994"},{"key":"ref4","article-title":"A survey on transformers in reinforcement learning","author":"Li","year":"2023","journal-title":"arXiv:2301.03044"},{"key":"ref5","first-page":"621","article-title":"Towards playing full MOBA games with deep reinforcement learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ye"},{"key":"ref6","article-title":"TiKick: Towards playing multi-agent football full games from single-agent demonstrations","author":"Huang","year":"2021","journal-title":"arXiv:2110.04507"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029475"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3095264"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/452"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2975428"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2939-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2010.06.019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.09.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref19","first-page":"1","article-title":"UNCLEAR: A straightforward method for continual reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kessler"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01758-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3162241"},{"key":"ref22","first-page":"1","article-title":"The infinite Gaussian mixture model","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"12","author":"Rasmussen"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/b11601500"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2884462"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00885"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927320"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref29","first-page":"97","article-title":"Minimum-delay adaptation in non-stationary reinforcement learning via online high-confidence change-point detection","volume-title":"Proc. Int. Conf. Auton. Agent. Multi. Agent Syst.","author":"Alegre"},{"issue":"9","key":"ref30","first-page":"142","article-title":"Online learning and stochastic approximations","volume":"17","author":"Bottou","year":"1998","journal-title":"Online Learn. Neural Netw."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223872"},{"key":"ref33","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020","journal-title":"arXiv:2009.09796"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref36","first-page":"1","article-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Riemer"},{"key":"ref37","first-page":"1","article-title":"Experience replay for continual learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Rolnick"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.050"},{"key":"ref39","first-page":"1","article-title":"Policy distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rusu"},{"key":"ref40","first-page":"1","article-title":"DisCoRL: Continual reinforcement learning via policy distillation","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Workshop","author":"Traore"},{"key":"ref41","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3170485"},{"key":"ref44","first-page":"1","article-title":"Near-optimal regret bounds for reinforcement learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"21","author":"Auer"},{"key":"ref45","article-title":"A sliding-window algorithm for Markov decision processes with arbitrarily changing rewards and transitions","author":"Gajane","year":"2018","journal-title":"arXiv:1805.10066"},{"key":"ref46","first-page":"81","article-title":"Variational regret bounds for reinforcement learning","volume-title":"Proc. Conf. Uncertain. Artif. Intell.","author":"Ortner"},{"key":"ref47","first-page":"1843","article-title":"Reinforcement learning for non-stationary Markov decision processes: The blessing of (more) optimism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheung"},{"key":"ref48","first-page":"3538","article-title":"A kernel-based approach to non-stationary reinforcement learning in metric spaces","volume-title":"Proc. Int. Conf. Uncertain. Artif. Intell.","author":"Domingues"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143872"},{"key":"ref50","first-page":"1","article-title":"Sequential decision-making under non-stationary environments via sequential change-point detection","volume-title":"Proc. Int. Workshop Learn. Multiple Contexts","author":"Hadoux"},{"key":"ref51","first-page":"1047","article-title":"Model-free non-stationarity detection and adaptation in reinforcement learning","volume-title":"Proc. Eur. Conf. Artif. Intell.","author":"Canonaco"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref53","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref54","article-title":"Revisiting discrete soft actor-critic","author":"Zhou","year":"2022","journal-title":"arXiv:2209.10081"},{"key":"ref55","article-title":"Deep online learning via meta-learning: Continual adaptation for model-based RL","author":"Nagabandi","year":"2018","journal-title":"arXiv:1812.07671"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"ref57","first-page":"1","article-title":"Sharing knowledge in multi-task deep reinforcement learning","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"D\u2019Eramo"},{"key":"ref58","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref59","first-page":"9443","article-title":"State entropy maximization with random encoders for efficient exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Seo"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref61","first-page":"1094","article-title":"Meta-World: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu"},{"key":"ref62","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref63","first-page":"26437","article-title":"Coordinated proximal policy optimization","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Wu"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10707065\/10145851.pdf?arnumber=10145851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T17:41:56Z","timestamp":1728409316000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10145851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":63,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3280085","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}