{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T21:51:24Z","timestamp":1730238684592,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"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":[[2023,11,9]]},"DOI":"10.1109\/icdl55364.2023.10364471","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:40:19Z","timestamp":1703533219000},"page":"150-155","source":"Crossref","is-referenced-by-count":0,"title":["Goal-Conditioned Flexible Object Manipulation by Self-Supervised Learning from Play"],"prefix":"10.1109","author":[{"given":"Keigo","family":"Ishii","sequence":"first","affiliation":[{"name":"Graduate School of Integrated Design Engineering, Keio University,Kanagawa,Japan"}]},{"given":"Shun","family":"Hiramatsu","sequence":"additional","affiliation":[{"name":"Graduate School of Integrated Design Engineering, Keio University,Kanagawa,Japan"}]},{"given":"Yuta","family":"Nomura","sequence":"additional","affiliation":[{"name":"Graduate School of Integrated Design Engineering, Keio University,Kanagawa,Japan"}]},{"given":"Shingo","family":"Murata","sequence":"additional","affiliation":[{"name":"Graduate School of Integrated Design Engineering, Keio University,Kanagawa,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8414"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6697007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.074"},{"key":"ref6","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref8","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Proceedings of the Conference on Robot Learning","volume":"100. PMLR","author":"Lynch","year":"2020"},{"key":"ref9","first-page":"564","article-title":"Learning predictive representations for deformable objects using contrastive estimation","volume-title":"Proceedings of the 2020 Conference on Robot Learning","volume":"155","author":"Yan","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811597"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.034"},{"key":"ref13","article-title":"Learning latent graph dynamics for deformable object manipulation","volume":"2","author":"Ma","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume-title":"Conference on Robot Learning","author":"Matas","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341608"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2633383"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989247"},{"key":"ref19","article-title":"Demonstration-bootstrapped autonomous practicing via multitask reinforcement learning","author":"Gupta","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref22","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"International conference on learning representations","author":"Higgins","year":"2017"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"issue":"11","key":"ref24","article-title":"Visualizing data using t-sne","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2023 IEEE International Conference on Development and Learning (ICDL)","start":{"date-parts":[[2023,11,9]]},"location":"Macau, China","end":{"date-parts":[[2023,11,11]]}},"container-title":["2023 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10364334\/10364349\/10364471.pdf?arnumber=10364471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T21:17:29Z","timestamp":1705094249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10364471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icdl55364.2023.10364471","relation":{},"subject":[],"published":{"date-parts":[[2023,11,9]]}}}