{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T10:36:17Z","timestamp":1725791777810},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,11]],"date-time":"2021-01-11T00:00:00Z","timestamp":1610323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,11]],"date-time":"2021-01-11T00:00:00Z","timestamp":1610323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,11]],"date-time":"2021-01-11T00:00:00Z","timestamp":1610323200000},"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":[[2021,1,11]]},"DOI":"10.1109\/ieeeconf49454.2021.9382621","type":"proceedings-article","created":{"date-parts":[[2021,3,24]],"date-time":"2021-03-24T20:14:35Z","timestamp":1616616875000},"page":"190-194","source":"Crossref","is-referenced-by-count":4,"title":["Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems"],"prefix":"10.1109","author":[{"given":"Taisuke","family":"Kobayashi","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"870","article-title":"Disentangled relational representations for explaining and learning from demonstration","author":"hristov","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8625038"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref12"},{"key":"ref13","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref14","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"coumans","year":"2016","journal-title":"Github Repository"},{"key":"ref15","first-page":"3758","article-title":"Visionbased multi-task manipulation for inexpensive robots using end-to-end learning from demonstration","author":"rahmatizadeh","year":"2018","journal-title":"IEEE International Conference on Robotics and Automation"},{"key":"ref16","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"in Advances in Neural Information Processing Systems Workshop"},{"key":"ref17","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1749-4699\/8\/1\/014008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010206"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref5","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"On the convergence of adam and beyond","author":"reddi","year":"2019","journal-title":"arXiv preprint arXiv 1904 01870"},{"key":"ref7","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref9","article-title":"Tadam: A robust stochastic gradient optimizer","author":"ilboudo","year":"2020","journal-title":"arXiv preprint arXiv 2003 07516"},{"key":"ref20","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1801 01000"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01510-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05788-0"}],"event":{"name":"2021 IEEE\/SICE International Symposium on System Integration (SII)","start":{"date-parts":[[2021,1,11]]},"location":"Iwaki, Fukushima, Japan","end":{"date-parts":[[2021,1,14]]}},"container-title":["2021 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9382420\/9382486\/09382621.pdf?arnumber=9382621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:44:10Z","timestamp":1652197450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9382621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,11]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf49454.2021.9382621","relation":{},"subject":[],"published":{"date-parts":[[2021,1,11]]}}}