{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:52:57Z","timestamp":1740102777011,"version":"3.37.3"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447360","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"191-195","source":"Crossref","is-referenced-by-count":1,"title":["UNeC: Unsupervised Exploring In Controllable Space"],"prefix":"10.1109","author":[{"given":"Xuantang","family":"Xiong","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}]},{"given":"Linghui","family":"Meng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation"}]},{"given":"Jingqing","family":"Ruan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation"}]},{"given":"Shuang","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref2"},{"article-title":"Solving rubik\u2019s cube with a robot hand","year":"2019","author":"Akkaya","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref5","first-page":"5639","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Laskin"},{"article-title":"Urlb: Unsupervised reinforcement learning benchmark","year":"2021","author":"Laskin","key":"ref6"},{"article-title":"Denoised mdps: Learning world models better than the world itself","year":"2022","author":"Wang","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref9"},{"key":"ref10","first-page":"18459","article-title":"Behavior from the void: Unsupervised active pre-training","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Diversity is all you need: Learning skills without a reward function","year":"2018","author":"Eysenbach","key":"ref11"},{"key":"ref12","first-page":"5171","article-title":"On variational bounds of mutual information","volume-title":"International Conference on Machine Learning","author":"Poole"},{"article-title":"Mastering atari with discrete world models","year":"2020","author":"Hafner","key":"ref13"},{"article-title":"Deepmind control suite","year":"2018","author":"Tassa","key":"ref14"},{"key":"ref15","first-page":"19","article-title":"Intrinsically motivated learning of hierarchical collections of skills","volume-title":"Proceedings of the 3rd International Conference on Development and Learning","volume":"112","author":"Barto"},{"key":"ref16","first-page":"8583","article-title":"Planning to explore via self-supervised world models","volume-title":"International Conference on Machine Learning","author":"Sekar"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981510"},{"key":"ref18","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"International Conference on Machine Learning","author":"Yarats"},{"article-title":"Dynamics-aware unsupervised discovery of skills","year":"2019","author":"Sharma","key":"ref20"},{"key":"ref21","first-page":"26078","article-title":"A mixture of surprises for unsupervised reinforcement learning","volume":"35","author":"Zhao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","first-page":"28598","article-title":"Mastering the unsupervised reinforcement learning benchmark from pixels","volume-title":"International Conference on Machine Learning","author":"Rajeswar"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17398"},{"article-title":"Gcs: graph-based coordination strategy for multi-agent reinforcement learning","year":"2022","author":"Ruan","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230493"},{"key":"ref26","first-page":"3480","article-title":"Learning task informed abstractions","volume-title":"International Conference on Machine Learning","author":"Fu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref29","first-page":"72","article-title":"Efficient selectivity and backup operators in monte-carlo tree search","volume-title":"International conference on computers and games","author":"Coulom"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3233\/faia230588"},{"article-title":"Dream to control: Learning behaviors by latent imagination","year":"2019","author":"Hafner","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43421-1_32"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447360.pdf?arnumber=10447360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:33:34Z","timestamp":1722573214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447360","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}