{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:57:03Z","timestamp":1770749823528,"version":"3.50.0"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005073","name":"Agency for Defense Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005073","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/lra.2022.3171915","type":"journal-article","created":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T19:37:55Z","timestamp":1651865875000},"page":"7455-7462","source":"Crossref","is-referenced-by-count":16,"title":["Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4105-4422","authenticated-orcid":false,"given":"Daesol","family":"Cho","sequence":"first","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3381-5241","authenticated-orcid":false,"given":"Jigang","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6819-1136","authenticated-orcid":false,"given":"H. Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","article-title":"Motion planner augmented reinforcement learning for robot manipulation in obstructed environments","volume-title":"Proc. Conf. Robot Learn.","author":"Yamada","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.053"},{"key":"ref4","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Eysenbach","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref6","article-title":"Exploration by random network distillation","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref7","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref8","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ostrovski","year":"2017"},{"key":"ref9","first-page":"2295","article-title":"A laplacian framework for option discovery in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Machado","year":"2017"},{"key":"ref10","article-title":"Unsupervised control through non-parametric discriminative rewards","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Warde-Farley","year":"2019"},{"key":"ref11","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pathak","year":"2019"},{"key":"ref12","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Sharma","year":"2020"},{"key":"ref13","article-title":"Mutual information-based state-control for intrinsically motivated reinforcement learning","author":"Zhao","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref15","article-title":"Composing task-agnostic policies with deep reinforcement learning","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Qureshi","year":"2020"},{"key":"ref16","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref17","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Adv. Neural Inf. Process. Syst. 33","author":"Yang","year":"2020"},{"key":"ref18","article-title":"Gradient surgery for multi-task learning","volume-title":"Adv. Neural Inf. Process. Syst. 33","author":"Yu","year":"2020"},{"key":"ref19","article-title":"Regularizing deep multi-task networks using orthogonal gradients","author":"Suteu","year":"2019"},{"key":"ref20","first-page":"3686","article-title":"MCP: Learning composable hierarchical control with multiplicative compositional policies","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Peng","year":"2019"},{"key":"ref21","first-page":"271","article-title":"F-GAN: Training generative neural samplers using variational divergence minimization","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Nowozin","year":"2016"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref24","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parisotto","year":"2020"},{"key":"ref25","article-title":"Neural methods for point-wise dependency estimation","volume-title":"Adv. Neural Inf. Process. Syst. 33","author":"Tsai","year":"2020"},{"key":"ref26","article-title":"Self-supervised representation learning with relative predictive coding","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Tsai","year":"2021"},{"key":"ref27","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref28","article-title":"Hindsight experience replay","volume-title":"Adv. Neural Inf. Process. Syst. 30","author":"Andrychowicz","year":"2017"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9750005\/09770346.pdf?arnumber=9770346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:43:10Z","timestamp":1705963390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9770346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":28,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3171915","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}