{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T10:22:44Z","timestamp":1768731764456,"version":"3.49.0"},"reference-count":68,"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":[{"name":"National Key R&D Program of China","award":["2022ZD0119801"],"award-info":[{"award-number":["2022ZD0119801"]}]},{"name":"National Nature Science Foundations of China","award":["U23A20388"],"award-info":[{"award-number":["U23A20388"]}]},{"name":"National Nature Science Foundations of China","award":["62021001"],"award-info":[{"award-number":["62021001"]}]},{"name":"National Nature Science Foundations of China","award":["U19B2026"],"award-info":[{"award-number":["U19B2026"]}]},{"name":"National Nature Science Foundations of China","award":["U19B2044"],"award-info":[{"award-number":["U19B2044"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2025.3529264","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T19:51:08Z","timestamp":1736797868000},"page":"3094-3110","source":"Crossref","is-referenced-by-count":2,"title":["Long-Term Feature Extraction via Frequency Prediction for Efficient Reinforcement Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9902-5723","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"given":"Mingxuan","family":"Ye","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"given":"Yufei","family":"Kuang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5137-9302","authenticated-orcid":false,"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-5579","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5723"},{"key":"ref4","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref5","article-title":"Unsupervised representation learning in deep reinforcement learning: A review","author":"Botteghi","year":"2022"},{"key":"ref6","first-page":"26517","article-title":"Efficient reinforcement learning in block MDPs: A model-free representation learning approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref7","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref8","article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Jaderberg"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798980"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20839"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26224"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539391"},{"key":"ref13","article-title":"Generalization in visual reinforcement learning with the reward sequence distribution","author":"Wang","year":"2023"},{"key":"ref14","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Schwarzer"},{"key":"ref15","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Hafner"},{"key":"ref16","first-page":"3875","article-title":"Bootstrap latent-predictive representations for multitask reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref17","first-page":"2459","article-title":"Prediction and control with temporal segment models","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Mishra"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2010.5684252"},{"key":"ref19","article-title":"neuro2vec: Masked fourier spectrum prediction for neurophysiological representation learning","author":"Wu","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11696"},{"key":"ref21","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref22","article-title":"State sequences prediction via fourier transform for representation learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ye"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.05.052"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae084"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102302"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref27","first-page":"7424","article-title":"Can increasing input dimensionality improve deep reinforcement learning?","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Ota"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref29","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref30","first-page":"8766","article-title":"Unsupervised state representation learning in Atari","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Anand"},{"key":"ref31","first-page":"2170","article-title":"DeepMDP: Learning continuous latent space models for representation learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Gelada"},{"key":"ref32","first-page":"30113","article-title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Castro"},{"key":"ref33","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Andrychowicz"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"key":"ref35","first-page":"7207","article-title":"Goal-aware prediction: Learning to model what matters","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Nair"},{"key":"ref36","article-title":"Contrastive learning as goal-conditioned reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Eysenbach"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92185-9_20"},{"key":"ref38","article-title":"Learning actionable representations with goal conditioned policies","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Ghosh"},{"key":"ref39","first-page":"8407","article-title":"Bisimulation makes analogies in goal-conditioned reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hansen-Estruch"},{"key":"ref40","first-page":"12602","article-title":"Curriculum-guided hindsight experience replay","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126620"},{"key":"ref42","first-page":"13464","article-title":"Exploration via hindsight goal generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106140"},{"key":"ref44","first-page":"113","article-title":"Energy-based hindsight experience prioritization","volume-title":"Proc. 2nd Annu. Conf. Robot Learn.","author":"Zhao"},{"key":"ref45","article-title":"Curiosity-driven experience prioritization via density estimation","author":"Zhao","year":"2019"},{"key":"ref46","article-title":"MHER: Model-based hindsight experience replay","author":"Yang","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/480"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102421"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref50","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref51","first-page":"30100","article-title":"Provable representation learning for imitation with contrastive fourier features","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref52","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref53","first-page":"10376","article-title":"Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Trott"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730390"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref57","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref58","first-page":"1514","article-title":"Automatic goal generation for reinforcement learning agents","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Florensa"},{"key":"ref59","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018"},{"key":"ref60","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref62","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref64","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. 33nd Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198572237.001.0001"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-32792-4"},{"key":"ref68","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10839463.pdf?arnumber=10839463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:42:27Z","timestamp":1741372947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10839463\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":68,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3529264","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}