{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T19:35:05Z","timestamp":1769542505065,"version":"3.49.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"major Science and Technology Innovation 2030","award":["2021ZD0112904"],"award-info":[{"award-number":["2021ZD0112904"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206307"],"award-info":[{"award-number":["62206307"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tetci.2023.3335944","type":"journal-article","created":{"date-parts":[[2023,12,7]],"date-time":"2023-12-07T14:54:23Z","timestamp":1701960863000},"page":"1181-1193","source":"Crossref","is-referenced-by-count":4,"title":["Dynamic Memory-Based Curiosity: A Bootstrap Approach for Exploration in Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5151-3381","authenticated-orcid":false,"given":"Zijian","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2632-5175","authenticated-orcid":false,"given":"Yiying","family":"Li","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5997-5169","authenticated-orcid":false,"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1385-0074","authenticated-orcid":false,"given":"Yuanzhao","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1236-8318","authenticated-orcid":false,"given":"Bo","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7587-8905","authenticated-orcid":false,"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6003-5748","authenticated-orcid":false,"given":"Xinjun","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3245-1901","authenticated-orcid":false,"given":"Huaimin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","first-page":"18459","article-title":"Behavior from the void: Unsupervised active pre-training","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu","year":"2021"},{"key":"ref5","first-page":"8114","article-title":"Novelty search in representational space for sample efficient exploration","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tao","year":"2020"},{"key":"ref6","article-title":"Exploration in deep reinforcement learning: A comprehensive survey","author":"Yang","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1006\/ceps.1999.1020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55509-6_4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55509-6_5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.108.2.311"},{"key":"ref13","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref14","first-page":"3875","article-title":"Bootstrap latent-predictive representations for multitask reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00591-010-0080-8"},{"key":"ref17","article-title":"Sample efficient deep reinforcement learning via uncertainty estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mai","year":"2022"},{"key":"ref18","first-page":"7498","article-title":"Simple and principled uncertainty estimation with deterministic deep learning via distance awareness","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8295.1950.tb00262.x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489075"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"ref24","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bellemare","year":"2016"},{"key":"ref25","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ostrovski","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/344"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref28","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pathak","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834710"},{"key":"ref30","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Osband","year":"2016"},{"key":"ref31","article-title":"Noisy networks for exploration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fortunato","year":"2018"},{"key":"ref32","article-title":"VIME: Variational information maximizing exploration","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Houthooft","year":"2016"},{"key":"ref33","first-page":"31855","article-title":"Byol-explore: Exploration by bootstrapped prediction","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Guo","year":"2022"},{"key":"ref34","volume-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning","author":"Szepesvri","year":"2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21959"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref38","first-page":"15220","article-title":"How to stay curious while avoiding noisy TVs using aleatoric uncertainty estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mavor-Parker"},{"key":"ref39","first-page":"2750","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tang","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3323628"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JCC56315.2022.00008"},{"key":"ref42","first-page":"8626","article-title":"Randomized prior functions for deep reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Osband","year":"2018"},{"key":"ref43","article-title":"Curiosity eliminates the exploration-exploitation dilemma","author":"Peterson","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00056-4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-016-1521-0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-7970-4"},{"key":"ref47","first-page":"13285","article-title":"Reducing variance in temporal-difference value estimation via ensemble of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang","year":"2022"},{"key":"ref48","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","volume-title":"Proc. Deep RL Workshop NeurIPS","author":"Achiam","year":"2016"},{"key":"ref49","first-page":"1311","article-title":"Automated curriculum learning for neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Graves","year":"2017"},{"key":"ref50","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen","year":"2017"},{"key":"ref51","article-title":"Learning fast, learning slow: A general continual learning method based on complementary learning system","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Arani","year":"2021"},{"key":"ref52","article-title":"URLB: Unsupervised reinforcement learning benchmark","volume-title":"Proc. Deep RL Workshop NeurIPS","author":"Laskin","year":"2021"},{"key":"ref53","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref55","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yarats","year":"2021"},{"key":"ref56","first-page":"34478","article-title":"Unsupervised reinforcement learning with contrastive intrinsic control","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Laskin","year":"2022"},{"key":"ref57","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref59","article-title":"Efficient exploration via state marginal matching","author":"Lee","year":"2019"},{"key":"ref60","first-page":"6736","article-title":"Aps: Active pretraining with successor features","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref62","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yarats","year":"2020"},{"key":"ref63","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schwarzer","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref65","first-page":"5580","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Kendall","year":"2017"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10480102\/10347362.pdf?arnumber=10347362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:05:34Z","timestamp":1769493934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10347362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2023.3335944","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}