{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:04:49Z","timestamp":1777655089695,"version":"3.51.4"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0116401,2019YFB2205401"],"award-info":[{"award-number":["2022ZD0116401,2019YFB2205401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076238,62222606,61834001,62025401"],"award-info":[{"award-number":["62076238,62222606,61834001,62025401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191424","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Mnemonic Dictionary Learning for Intrinsic Motivation in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Renye","family":"Yan","sequence":"first","affiliation":[{"name":"School of Software & Microelectronics, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhan","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pin","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of the Integrated Circuits, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yimao","family":"Cai","sequence":"additional","affiliation":[{"name":"School of the Integrated Circuits, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"3360","article-title":"EMI: Exploration with mutual information","author":"kim","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref35","first-page":"13499","article-title":"Exploration via hindsight goal generation","author":"ren","year":"2019","journal-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref34","first-page":"1","article-title":"Learning actionable representations with goal conditioned policies","author":"ghosh","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/733"},{"key":"ref37","first-page":"2721","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref14","first-page":"5565","article-title":"Latent world models for intrinsically motivated exploration","author":"ermolov","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref31","first-page":"1","article-title":"Never give up: Learning directed exploration strategies","author":"badia","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref30","first-page":"1","article-title":"Exploration by random network distillation","author":"burda","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref33","first-page":"3878","article-title":"Self-imitation learning","author":"oh","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref10","first-page":"2721","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"volodymyr","year":"2015","journal-title":"Nature"},{"key":"ref17","first-page":"1","article-title":"Exploration via elliptical episodic bonuses","author":"henaff","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref39","first-page":"1","article-title":"Large-scale study of curiosity-driven learning","author":"burda","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref16","first-page":"1","article-title":"Improving intrinsic exploration with language abstractions","author":"mu","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"2125","author":"mohamed","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"263","article-title":"#exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"16223","article-title":"The importance of non-markovianity in maximum state entropy exploration","author":"mutti","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1126\/science.aaw4325","article-title":"Memory engrams: Recalling the past and imagining the future","volume":"367","author":"josselyn","year":"2020","journal-title":"Science"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553463"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref25","first-page":"19","article-title":"Online learning for matrix factorization and sparse coding","volume":"11","author":"mairal","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","first-page":"5125","author":"machado","year":"2020","journal-title":"Count-based exploration with the successor representation"},{"key":"ref42","first-page":"2469","article-title":"Policy optimization with demonstrations","author":"kang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref41","first-page":"2917","article-title":"Hierarchical imitation and reinforcement learning","author":"le","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/290"},{"key":"ref44","article-title":"Efficient sparse coding algorithms","volume":"19","author":"lee","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"1","article-title":"Episodic curiosity through reachability","author":"savinov","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref43","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"2753","article-title":"Exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"2471","author":"martin","year":"2017","journal-title":"Count-based exploration in feature space for reinforcement learning"},{"key":"ref29","article-title":"Deep curiosity search: Intra-life exploration improves performance on challenging deep reinforcement learning problems","author":"stanton","year":"2018","journal-title":"Advances in Neural Information Processing Systems Deep Reinforcement Learning Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780195399820.013.0010"},{"key":"ref9","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16981"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236361"},{"key":"ref40","first-page":"1087","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","location":"Gold Coast, Australia","start":{"date-parts":[[2023,6,18]]},"end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191424.pdf?arnumber=10191424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:04Z","timestamp":1692639724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191424","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}