{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T04:22:19Z","timestamp":1743740539024,"version":"3.40.3"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650970","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Autoencoder Reconstruction Model for Long-Horizon Exploration"],"prefix":"10.1109","author":[{"given":"Renye","family":"Yan","sequence":"first","affiliation":[{"name":"Peiking University,School of Integrated Circuits,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University,Software Institute,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaozhong","family":"Gan","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfan","family":"Yang","sequence":"additional","affiliation":[{"name":"Peiking University,School of Integrated Circuits,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoke","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongxi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Liang","sequence":"additional","affiliation":[{"name":"Peiking University,School of Integrated Circuits,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yimao","family":"Cai","sequence":"additional","affiliation":[{"name":"Peiking University,School of Integrated Circuits,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"article-title":"Never give up: Learning directed exploration strategies","year":"2020","author":"Badia","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1_2"},{"article-title":"Large-scale study of curiosity-driven learning","year":"2018","author":"Burda","key":"ref4"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2013.00025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref9","first-page":"29","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Curiosity-driven exploration in deep reinforcement learning via bayesian neural networks","year":"2016","author":"Houthooft","key":"ref10"},{"key":"ref11","first-page":"29","article-title":"Vime: Variational information maximizing exploration","author":"Houthooft","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16981"},{"key":"ref13","first-page":"3360","article-title":"EMI: Exploration with mutual information","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref14","first-page":"12","article-title":"Actor-critic algorithms","author":"Konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5955"},{"issue":"2","key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/344"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref20","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Icml","volume":"99","author":"Ng"},{"key":"ref21","first-page":"3878","article-title":"Self-imitation learning","volume-title":"International Conference on Machine Learning","author":"Oh"},{"key":"ref22","first-page":"2721","author":"Ostrovski","year":"2017","journal-title":"Count-based exploration with neural density models"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/bs.pbr.2016.05.005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.12.006.2007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref27","first-page":"627","author":"Ross","year":"2011","journal-title":"A reduction of imitation learning and structured prediction to no-regret online learning"},{"article-title":"Episodic curiosity through reachability","year":"2018","author":"Savinov","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref30","first-page":"1889","author":"Schulman","year":"2015","journal-title":"Trust region policy optimization"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref36","first-page":"4","article-title":"A study of count-based exploration for deep reinforcement learning","volume-title":"Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS)","author":"Tang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16111-7_23"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/290"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650970.pdf?arnumber=10650970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T17:46:56Z","timestamp":1743702416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650970","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}