{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T06:02:08Z","timestamp":1776578528555,"version":"3.51.2"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018550","name":"Science and Technology Innovation 2030 New Generation Artificial Intelligence Major Project","doi-asserted-by":"publisher","award":["2021ZD0113303"],"award-info":[{"award-number":["2021ZD0113303"]}],"id":[{"id":"10.13039\/501100018550","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192783"],"award-info":[{"award-number":["62192783"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276128"],"award-info":[{"award-number":["62276128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276142"],"award-info":[{"award-number":["62276142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206133"],"award-info":[{"award-number":["62206133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Nanjing International\/Hong Kong, Macau, and Taiwan Science and Technology Cooperation Plan","award":["202308031"],"award-info":[{"award-number":["202308031"]}]},{"name":"Jiangning District Science and Technology Small and Medium Enterprises Technology Innovation Special Fund Project","award":["2024CZ08"],"award-info":[{"award-number":["2024CZ08"]}]},{"DOI":"10.13039\/100017085","name":"Collaborative Innovation Center of Novel Software Technology and Industrialization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017085","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":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3467338","type":"journal-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T13:31:51Z","timestamp":1729258311000},"page":"13608-13614","source":"Crossref","is-referenced-by-count":1,"title":["State Abstraction via Deep Supervised Hash Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4937-0568","authenticated-orcid":false,"given":"Guang","family":"Yang","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3486-6864","authenticated-orcid":false,"given":"Zheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8504-455X","authenticated-orcid":false,"given":"Jing","family":"Huo","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5379-9539","authenticated-orcid":false,"given":"Shangdong","family":"Yang","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Big Data Security and Intelligent Processing, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8445-4330","authenticated-orcid":false,"given":"Tianyu","family":"Ding","sequence":"additional","affiliation":[{"name":"Applied Sciences Group, Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8757-1767","authenticated-orcid":false,"given":"Xingguo","family":"Chen","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Big Data Security and Intelligent Processing, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-1813","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019876"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981612"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200726"},{"issue":"71","key":"ref4","first-page":"1","article-title":"Policy gradient methods in the presence of symmetries and state abstractions","volume":"25","author":"Panangaden","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","first-page":"361","article-title":"Reinforcement learning with soft state aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Singh"},{"key":"ref6","first-page":"2915","article-title":"Near optimal behavior via approximate state abstraction","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Abel"},{"key":"ref7","first-page":"1","article-title":"Towards a unified theory of state abstraction for mdps","volume-title":"Proc. Int. Symp. Artif. Intell. Math.","author":"Li"},{"key":"ref8","first-page":"834","article-title":"Abstraction selection in model-based reinforcement learning","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref9","first-page":"106","article-title":"Model minimization in Markov decision processes","volume-title":"Proc. 9th AAAI Conf. Artif. Intell.","author":"Dean"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00376-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref12","first-page":"1649","article-title":"Bounding performance loss in approximate MDP homomorphisms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Taylor"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6564"},{"key":"ref14","first-page":"124","article-title":"Model reduction techniques for computing approximately optimal solutions for Markov decision processes","volume-title":"Proc. 13th Conf. Uncertain. Artifi. Intell.","author":"Dean"},{"key":"ref15","first-page":"2455","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bengio"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3109284"},{"key":"ref17","article-title":"State abstractions for generalization in reinforcement learning","author":"Zhang","year":"2021"},{"key":"ref18","first-page":"2170","article-title":"DeepMDP: Learning continuous latent space models for representation learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Gelada"},{"key":"ref19","first-page":"8229","article-title":"Learning Markov state abstractions for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Allen"},{"key":"ref20","first-page":"20189","article-title":"Continuous MDP homomorphisms and homomorphic policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 36","author":"Rezaei-Shoshtari"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3296642"},{"key":"ref22","first-page":"1","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc. 9th Int. Conf. Learn. Repr.","author":"Zhang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013134"},{"key":"ref24","first-page":"30113","article-title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Castro"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20883"},{"key":"ref26","first-page":"2482","article-title":"Deep supervised discrete hashing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2997020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3282921"},{"key":"ref30","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3264151"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26116"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3379089"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2371046"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref36","first-page":"3713","article-title":"Target-based temporal-difference learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref37","volume-title":"Functional Analysis","author":"Yosida","year":"2012"},{"key":"ref38","first-page":"1856","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"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10723098.pdf?arnumber=10723098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:49:10Z","timestamp":1752169750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10723098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":38,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3467338","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}