{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:51:02Z","timestamp":1772823062055,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202008050300"],"award-info":[{"award-number":["202008050300"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Grant of the Graduate School of Information Science and Electrical Engineering (ISEE) of Kyushu University for Supporting Students' Participation in International Conferences"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tnnls.2023.3344880","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T14:52:40Z","timestamp":1704725560000},"page":"2368-2381","source":"Crossref","is-referenced-by-count":3,"title":["Compact Goal Representation Learning via Information Bottleneck in Goal-Conditioned Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6683-0056","authenticated-orcid":false,"given":"Qiming","family":"Zou","sequence":"first","affiliation":[{"name":"Graduate School of Systems Life Sciences, Kyushu University, Fukuoka, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7743-6177","authenticated-orcid":false,"given":"Einoshin","family":"Suzuki","sequence":"additional","affiliation":[{"name":"Graduate School and Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9209","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Proc. NIPS","author":"Nair"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059912"},{"key":"ref5","first-page":"1317","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","volume-title":"Proc. ICML","volume":"119","author":"Campos"},{"key":"ref6","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Proc. CoRL","author":"Gupta"},{"key":"ref7","first-page":"1094","article-title":"Learning to achieve goals","volume-title":"Proc. IJCAI","author":"Kaelbling"},{"key":"ref8","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. ICML","author":"Schaul"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"key":"ref10","article-title":"InfoBot: Transfer and exploration via the information bottleneck","volume-title":"Proc. ICLR","author":"Goyal"},{"key":"ref11","first-page":"8407","article-title":"Bisimulation makes analogies in goal-conditioned reinforcement learning","volume-title":"Proc. ICML","author":"Hansen-Estruch"},{"key":"ref12","first-page":"3885","article-title":"Discrete compositional representations as an abstraction for goal conditioned reinforcement learning","volume-title":"Proc. NIPS","author":"Islam"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2010.04.006"},{"key":"ref14","first-page":"7783","article-title":"Skew-fit: State-covering self-supervised reinforcement learning","volume-title":"Proc. ICML","author":"Pong"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92185-9_20"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17120"},{"key":"ref18","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. NIPS","author":"Andrychowicz"},{"key":"ref19","first-page":"12602","article-title":"Curriculum-guided hindsight experience replay","volume-title":"Proc. NIPS","author":"Fang"},{"key":"ref20","first-page":"7754","article-title":"Generalized hindsight for reinforcement learning","volume-title":"Proc. NIPS","author":"Li"},{"key":"ref21","first-page":"13956","article-title":"Generalization in reinforcement learning with selective noise injection and information bottleneck","volume-title":"Proc. NIPS","author":"Igl"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.101"},{"key":"ref23","first-page":"27813","article-title":"Robust predictable control","volume-title":"Proc. NIPS","author":"Eysenbach"},{"key":"ref24","first-page":"17007","article-title":"Dynamic bottleneck for robust self-supervised exploration","volume-title":"Proc. NIPS","volume":"34","author":"Bai"},{"key":"ref25","first-page":"11890","article-title":"Predictive information accelerates learning in RL","volume-title":"Proc. NIPS","author":"Lee"},{"key":"ref26","first-page":"3686","article-title":"Deep reinforcement and InfoMax learning","volume-title":"Proc. NIPS","author":"Mazoure"},{"key":"ref27","first-page":"8114","article-title":"Novelty search in representational space for sample efficient exploration","volume-title":"Proc. NIPS","author":"Tao"},{"key":"ref28","first-page":"26345","article-title":"Which mutual-information representation learning objectives are sufficient for control?","volume-title":"Proc. NIPS","author":"Rakelly"},{"key":"ref29","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref30","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref32","volume-title":"YOLO by Ultralytics","author":"Jocher","year":"2023"},{"key":"ref33","first-page":"368","article-title":"The information bottleneck method","volume-title":"Proc. Allerton Conf. Commun., Control, Comput.","author":"Tishby"},{"issue":"4","key":"ref34","first-page":"305","article-title":"Completeness, similar regions, and unbiased estimation-Part I","volume":"10","author":"Lehmann","year":"1950","journal-title":"Sankhya, Indian J. Statist."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref36","first-page":"531","article-title":"Towards a unified theory of state abstraction for MDPs","volume-title":"Proc. ISAIM","author":"Li"},{"key":"ref37","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref38","article-title":"Deep variational information bottleneck","volume-title":"Proc. ICLR","author":"Alemi"},{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref40","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv:1802.09464"},{"key":"ref41","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989164"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref45","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. NIPS","author":"Kumar"},{"key":"ref46","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. NIPS","author":"Laskin"},{"key":"ref47","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. ICLR","author":"Kostrikov"},{"key":"ref48","article-title":"Rethinking goal-conditioned supervised learning and its connection to offline RL","volume-title":"Proc. ICLR","author":"Yang"},{"key":"ref49","first-page":"21579","article-title":"Generating adjacency-constrained subgoals in hierarchical reinforcement learning","volume-title":"Proc. NIPS","author":"Zhang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10877690\/10382708.pdf?arnumber=10382708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:17Z","timestamp":1764959957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10382708\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":51,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3344880","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}