{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:11:48Z","timestamp":1762254708259,"version":"3.37.3"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"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":["2020YFB1313600"],"award-info":[{"award-number":["2020YFB1313600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62003381","U1813202"],"award-info":[{"award-number":["62003381","U1813202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tcds.2023.3339215","type":"journal-article","created":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T19:55:06Z","timestamp":1702324506000},"page":"1121-1133","source":"Crossref","is-referenced-by-count":3,"title":["Stable Exploration via Imitating Highly Scored Episode-Decayed Exploration Episodes in Procedurally Generated Environments"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4549-1221","authenticated-orcid":false,"given":"Mao","family":"Xu","sequence":"first","affiliation":[{"name":"School of Automation and the Institute for Future, Qingdao University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5549-312X","authenticated-orcid":false,"given":"Shuzhi","family":"Sam Ge","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9881-3705","authenticated-orcid":false,"given":"Dongjie","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Automation and the Institute for Future, Qingdao University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3758-237X","authenticated-orcid":false,"given":"Qian","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Physics and Telecommunication Engineering, Zhoukou Normal University, Zhoukou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1038\/nature14236"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.13140\/RG.2.2.18893.74727"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TITS.2021.3054625"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TCDS.2020.3039859"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TCDS.2019.2928820"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICRA48506.2021.9561891"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1038\/nature24270"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1126\/science.aam6960"},{"key":"ref9","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bellemare","year":"2016"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref11","first-page":"1","article-title":"Large-scale study of curiosity-driven learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref12","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref13","first-page":"1","article-title":"Never give up: Learning directed exploration strategies","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Badia","year":"2020"},{"key":"ref14","first-page":"6553","article-title":"Towards generalization and simplicity in continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Rajeswaran","year":"2017"},{"year":"2018","author":"Zhang","article-title":"A study on overfitting in deep Reinforcement Learning","key":"ref15"},{"year":"2018","author":"Chevalier-Boisvert","article-title":"Minimalistic gridworld environment for OpenAI Gym","key":"ref16"},{"author":"Chevalier-Boisvert","article-title":"MiniWorld: Minimalistic 3D environment for RL & robotics research","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.24963\/ijcai.2019\/373"},{"key":"ref19","first-page":"1","article-title":"RIDE: Rewarding impact-driven exploration for procedurally-generated environments","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Raileanu","year":"2020"},{"year":"2020","author":"Zhang","article-title":"BeBold: Exploration beyond the boundary of explored regions","key":"ref20"},{"key":"ref21","first-page":"1","article-title":"Rank the episodes: A simple approach for exploration in procedurally-generated environments","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zha","year":"2021"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ITA.2018.8503252"},{"key":"ref23","first-page":"4033","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Osband","year":"2016"},{"year":"2018","author":"Nichol","article-title":"Gotta learn fast: A new benchmark for generalization in RL","key":"ref24"},{"key":"ref25","first-page":"1","article-title":"Learning with AMIGo: Adversarially motivated intrinsic goals","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Campero","year":"2021"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/MRA.2010.936952"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/TCSVT.2020.3039522"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.18653\/v1\/N19-1268"},{"year":"2015","author":"Schaul","article-title":"Prioritized experience replay","key":"ref29"},{"key":"ref30","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh","year":"2018"},{"year":"2017","author":"Schulman","article-title":"Proximal policy optimization algorithms","key":"ref31"},{"year":"2016","author":"Bojarski","article-title":"End to end learning for self-driving cars","key":"ref32"},{"key":"ref33","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho","year":"2016"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref35","first-page":"1","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tang","year":"2017"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10552653\/10352435.pdf?arnumber=10352435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:08:34Z","timestamp":1719349714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10352435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":35,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2023.3339215","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}