{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T10:45:05Z","timestamp":1781779505458,"version":"3.54.5"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020YFB1807700"],"award-info":[{"award-number":["2020YFB1807700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tai.2022.3185180","type":"journal-article","created":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T15:46:57Z","timestamp":1655826417000},"page":"1154-1164","source":"Crossref","is-referenced-by-count":13,"title":["R\u00e9nyi State Entropy Maximization for Exploration Acceleration in Reinforcement Learning"],"prefix":"10.1109","volume":"4","author":[{"given":"Mingqi","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3316-5381","authenticated-orcid":false,"given":"Man-On","family":"Pun","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"issue":"3\/4","key":"ref2","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1023\/A:1022676722315","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref3","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"Stadie","year":"2015"},{"issue":"7553","key":"ref4","first-page":"436","article-title":"Deep Learning","volume-title":"Nature","volume":"521","author":"LeCun","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCBDA.2017.7951951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143949"},{"key":"ref8","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref9","article-title":"Efficient exploration via state marginal matching","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref11","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ostrovski","year":"2017"},{"key":"ref12","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bellemare","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref14","first-page":"10925","article-title":"Intrinsic reward driven imitation learning via generative model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2020"},{"key":"ref15","first-page":"1","article-title":"Large-scale study of curiosity-driven learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref16","article-title":"Go-explore: A new approach for hard-exploration problems","author":"Ecoffet","year":"2019"},{"key":"ref17","article-title":"Never give up: Learning directed exploration strategies","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Badia","year":"2020"},{"key":"ref18","article-title":"RIDE: Rewarding impact-driven exploration for procedurally-generated environments","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Raileanu","year":"2020"},{"key":"ref19","article-title":"Episodic curiosity through reachability","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Savinov","year":"2019"},{"key":"ref20","first-page":"9443","article-title":"State entropy maximization with random encoders for efficient exploration","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Seo","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/01966324.2003.10737616"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17297"},{"key":"ref23","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0166-218X(92)90177-C"},{"key":"ref25","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hazan","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOS539"},{"key":"ref27","article-title":"A simple maze environment","author":"Chan"},{"key":"ref28","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref29","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ioffe","year":"2015"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref31","article-title":"Pytorch implementation of the reinforcement learning algorithms","author":"Kostrikov"},{"key":"ref32","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2015"},{"key":"ref33","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2018"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10261321\/09802917.pdf?arnumber=9802917","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:42Z","timestamp":1755911322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9802917\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":33,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3185180","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}