{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T18:38:38Z","timestamp":1779215918510,"version":"3.51.4"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0116403"],"award-info":[{"award-number":["2022ZD0116403"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"Postdoctoral Fellowship Program of the China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["GZC20232995"],"award-info":[{"award-number":["GZC20232995"]}],"id":[{"id":"10.13039\/501100002858","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":[[2025,9]]},"DOI":"10.1109\/tsmc.2025.3574024","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T13:43:20Z","timestamp":1749735800000},"page":"5776-5789","source":"Crossref","is-referenced-by-count":1,"title":["Exploration via Embracing Diversity in Reinforcement Learning for Sparse-Reward Procedurally-Generated Tasks"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1766-5634","authenticated-orcid":false,"given":"Pei","family":"Xu","sequence":"first","affiliation":[{"name":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5982-0615","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Emergency Management Science and Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7483-1817","authenticated-orcid":false,"given":"Wenjie","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer and Data Science, Fuzhou University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-9273","authenticated-orcid":false,"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3000073"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3228901"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3209070"},{"key":"ref4","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Riedmiller"},{"key":"ref5","first-page":"1","article-title":"Towards generalization and simplicity in continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rajeswaran"},{"key":"ref6","article-title":"A dissection of overfitting and generalization in continuous reinforcement learning","author":"Zhang","year":"2018","journal-title":"arXiv:1806.07937"},{"key":"ref7","article-title":"Minimalistic Gridworld environment for OpenAI gym.","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/373"},{"key":"ref9","first-page":"1","article-title":"RIDE: Rewarding impact-driven exploration for procedurally-generated environments","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Raileanu"},{"key":"ref10","first-page":"1","article-title":"Learning with AMIGo: Adversarially motivated intrinsic goals","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Campero"},{"key":"ref11","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bellemare"},{"key":"ref12","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Burda"},{"key":"ref13","article-title":"MiniWorld: Minimalistic 3D environment for RL and robotics research.","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref14","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe"},{"key":"ref15","first-page":"1","article-title":"Rank the episodes: A simple approach for exploration in procedurally-generated environments","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zha"},{"key":"ref16","first-page":"1","article-title":"Adversarially guided actor-critic","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Flet-Berliac"},{"key":"ref17","first-page":"25217","article-title":"NoveLD: A simple yet effective exploration criterion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref18","article-title":"Contextual Markov decision processes","author":"Hallak","year":"2015","journal-title":"arXiv:1502.02259"},{"key":"ref19","article-title":"The NetHack learning environment","author":"K\u00fcttler","year":"2020","journal-title":"arXiv:2006.13760"},{"key":"ref20","article-title":"Exploration via elliptical episodic bonuses","author":"Henaff","year":"2022","journal-title":"arXiv:2210.05805"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref25","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref29","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref31","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref32","article-title":"Noisy networks for exploration","author":"Fortunato","year":"2017","journal-title":"arXiv:1706.10295"},{"key":"ref33","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref35","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref36","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref37","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/32"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26384"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref42","first-page":"2721","article-title":"Countbased exploration with neural density models","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Ostrovski"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3134259"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/37"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2017.70"},{"key":"ref46","article-title":"Large-scale study of curiosity-driven learning","author":"Burda","year":"2018","journal-title":"arXiv:1808.04355"},{"key":"ref47","first-page":"1","article-title":"Episodic curiosity through reachability","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Savinov"},{"key":"ref48","article-title":"Never give up: Learning directed exploration strategies","author":"Badia","year":"2020","journal-title":"arXiv:2002.06038"},{"key":"ref49","first-page":"9663","article-title":"Made: Exploration via maximizing deviation from explored regions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref50","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh"},{"key":"ref51","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hazan"},{"key":"ref52","first-page":"1","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jin"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl242"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s40595-015-0045-x"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11130413\/11033165.pdf?arnumber=11033165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T06:16:53Z","timestamp":1755670613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11033165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":54,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3574024","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}