{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:40:14Z","timestamp":1759236014453,"version":"3.44.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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","award":["62373242","92248303"],"award-info":[{"award-number":["62373242","92248303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tsmc.2025.3578730","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:48:42Z","timestamp":1752169722000},"page":"7012-7023","source":"Crossref","is-referenced-by-count":0,"title":["Learning Hidden Transition for Nonstationary Environments With Multistep Tree Search"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2237-7330","authenticated-orcid":false,"given":"Yangqing","family":"Fu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8901-9335","authenticated-orcid":false,"given":"Yue","family":"Gao","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3248120"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2022.108678"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3020732"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3001355"},{"key":"ref5","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","volume-title":"arXiv:1712.01815","author":"Silver","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3182328"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechmachtheory.2021.104635"},{"key":"ref9","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"arXiv:1803.11347","author":"Nagabandi","year":"2018"},{"key":"ref10","first-page":"1","article-title":"Deep online learning via meta-learning: Continual adaptation for model-based RL","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nagabandi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17061"},{"key":"ref12","first-page":"941","article-title":"Learning action representations for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chandak"},{"key":"ref13","first-page":"4300","article-title":"Non-stationary reinforcement learning without prior knowledge: An optimal black-box approach","volume-title":"Proc. Conf. Learn. Theory","author":"Wei"},{"key":"ref14","article-title":"Rl\u00b2: Fast reinforcement learning via slow reinforcement learning","volume-title":"arXiv:1611.02779","author":"Duan","year":"2016"},{"key":"ref15","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref17","first-page":"1861","article-title":"Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref18","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref19","first-page":"61008","article-title":"Accelerating monte carlo tree search with probability tree state abstraction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Fu"},{"key":"ref20","first-page":"11393","article-title":"Deep reinforcement learning amidst continual structured non-stationarity","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"ref22","first-page":"1","article-title":"Learning against non-stationary agents with opponent modelling and deep reinforcement learning","volume-title":"Proc. AAAI Spring Symposia","author":"Everett"},{"key":"ref23","first-page":"1","article-title":"Planning in stochastic environments with a learned model","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Antonoglou"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9661"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2973761"},{"key":"ref26","first-page":"4476","article-title":"Learning and planning in complex action spaces","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hubert"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2899613"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2190298"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2844399"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3129160"},{"key":"ref31","first-page":"640","article-title":"VIREL: A variational inference framework for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Fellows"},{"key":"ref32","first-page":"64","article-title":"Recurrent neural networks","volume":"5","author":"Medsker","year":"2001","journal-title":"Design Appl."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"arXiv:1412.3555","author":"Chung","year":"2014"},{"key":"ref35","first-page":"25476","article-title":"Mastering atari games with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ye"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3270298"},{"key":"ref37","first-page":"3769","article-title":"Monte-carlo tree search as regularized policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Grill"},{"key":"ref38","article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","volume-title":"arXiv:2009.12293","author":"Zhu","year":"2020"},{"key":"ref39","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":"ref40","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref41","first-page":"35449","article-title":"An adaptive deep RL method for non-stationary environments with piecewise stable context","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chen"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11173422\/11076163.pdf?arnumber=11076163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:27:46Z","timestamp":1759235266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11076163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":41,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3578730","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"type":"print","value":"2168-2216"},{"type":"electronic","value":"2168-2232"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}