{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T04:21:06Z","timestamp":1754108466049,"version":"3.37.3"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010418","name":"IITP","doi-asserted-by":"publisher","award":["2018-0-00622-RMI\/20%,2019-0-01371-BabyMind\/20%,2015-0-00310-SW.StarLab\/10%,2021-0-02068-AIHub\/10%"],"award-info":[{"award-number":["2018-0-00622-RMI\/20%,2019-0-01371-BabyMind\/20%,2015-0-00310-SW.StarLab\/10%,2021-0-02068-AIHub\/10%"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003661","name":"KIAT","doi-asserted-by":"publisher","award":["P0006720-ILIAS\/10%"],"award-info":[{"award-number":["P0006720-ILIAS\/10%"]}],"id":[{"id":"10.13039\/501100003661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811858","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"5553-5559","source":"Crossref","is-referenced-by-count":9,"title":["From Scratch to Sketch: Deep Decoupled Hierarchical Reinforcement Learning for Robotic Sketching Agent"],"prefix":"10.1109","author":[{"given":"Ganghun","family":"Lee","sequence":"first","affiliation":[{"name":"Interdisciplinary Program in Cognitive Science, Seoul National University,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minji","family":"Kim","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in Neuroscience, Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsu","family":"Lee","sequence":"additional","affiliation":[{"name":"AIIS, Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byoung-Tak","family":"Zhang","sequence":"additional","affiliation":[{"name":"Seoul National University,Dept. of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref31","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref30","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223533"},{"key":"ref11","article-title":"Deep reinforcement learning for autonomous driving: A survey","author":"kiran","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011438"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01167-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","article-title":"Unsuper-vised doodling and painting with improved spiral","author":"mellor","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/3101120"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2013.01.012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793484"},{"key":"ref28","article-title":"Planning with goal-conditioned policies","author":"nasiriany","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Strokenet: A neural painting en-vironment","author":"zheng","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref27","article-title":"Many-goals reinforcement learning","author":"veeriah","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"A neural representation of sketch drawings","author":"ha","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"1666","article-title":"Synthesizing programs for images using reinforced adversarial learning","author":"ganin","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref29","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00880"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2015.7373001"},{"key":"ref7","article-title":"Content masked loss: Human-like brush stroke planning in a reinforcement learning painting agent","author":"schaldenbrand","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2003.1210867"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/app10103396"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10020054"},{"key":"ref20","article-title":"Why does hierarchy (sometimes) work so well in reinforcement learning?","author":"nachum","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref24","first-page":"167","article-title":"Hierarchical learning in stochastic domains: Prelim-inary results","volume":"951","author":"kaelbling","year":"0","journal-title":"Proceedings of the Tenth International Conference on Machine Learning"},{"key":"ref23","article-title":"Hierarchical actor-critic","volume":"12","author":"levy","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.29007\/83qp"},{"key":"ref25","article-title":"Unsupervised control through non-parametric discrim-inative rewards","author":"warde-farley","year":"2018","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2022,5,23]]},"location":"Philadelphia, PA, USA","end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811858.pdf?arnumber=9811858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:35Z","timestamp":1667516735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811858\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811858","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}