{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T16:02:19Z","timestamp":1772208139601,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533820","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Unsupervised Discovery of Transitional Skills for Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Qiangxing","family":"Tian","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Jinxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Guanchu","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China"}]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1006\/ceps.1999.1020"},{"key":"ref12","author":"eysenbach","year":"2018","journal-title":"Diversity is all you need Learning skills without a reward function"},{"key":"ref13","author":"gregor","year":"2016","journal-title":"Variational Intrinsic Control"},{"key":"ref14","author":"sharma","year":"2019","journal-title":"Dynamics-aware unsupervised discovery of skills"},{"key":"ref15","author":"liu","year":"2021","journal-title":"Learn goal-conditioned policy with intrinsic motivation for deep reinforcement learning"},{"key":"ref16","author":"nachum","year":"2018","journal-title":"Data-efficient hierarchical reinforcement learning"},{"key":"ref17","author":"lee","year":"2018","journal-title":"Com-posing complex skills by learning transition policies"},{"key":"ref18","first-page":"5320","article-title":"Robust imitation of diverse behaviors","author":"wang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","author":"tian","year":"0","journal-title":"Independent skill transfer for deep reinforcement learning"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Computer Science"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref27","author":"haarnoja","year":"2018","journal-title":"Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor"},{"key":"ref3","author":"pong","year":"2019","journal-title":"Skew-fit State-covering self-supervised reinforcement learning"},{"key":"ref6","article-title":"Model-based reinforcement learning for atari","volume":"abs 1903 374","author":"kaiser","year":"2019","journal-title":"CoRR"},{"key":"ref29"},{"key":"ref5","author":"warde-farley","year":"2018","journal-title":"Unsupervised Control Through Non-Parametric Discriminative Rewards"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref7","article-title":"Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation","volume":"abs 1811 10092","author":"wang","year":"2018","journal-title":"CoRR"},{"key":"ref2","author":"lee","year":"2020","journal-title":"Weakly-supervised reinforcement learning for controllable behavior"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref1","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref20","author":"riedmiller","year":"2018","journal-title":"Learning by playing-solving sparse reward tasks from scratch"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref21","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","author":"chentanez","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.12.006.2007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2013.00037"},{"key":"ref26","article-title":"The im algorithm: a variational approach to information maximization","author":"barber","year":"2003","journal-title":"NIPS 2003"},{"key":"ref25","article-title":"Curiosity driven reinforcement learning for motion planning on humanoids","author":"frank","year":"2013","journal-title":"Frontiers in Neurorobotics"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533820.pdf?arnumber=9533820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:32:26Z","timestamp":1659483146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533820","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}