{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:56:11Z","timestamp":1776110171078,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561081","type":"proceedings-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T20:28:35Z","timestamp":1634675315000},"page":"4627-4633","source":"Crossref","is-referenced-by-count":15,"title":["TRANS-AM: Transfer Learning by Aggregating Dynamics Models for Soft Robotic Assembly"],"prefix":"10.1109","author":[{"given":"Kazutoshi","family":"Tanaka","sequence":"first","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}]},{"given":"Ryo","family":"Yonetani","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}]},{"given":"Masashi","family":"Hamaya","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}]},{"given":"Robert","family":"Lee","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}]},{"given":"Felix von","family":"Drigalski","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}]},{"given":"Yoshihisa","family":"Ijiri","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967293"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2017.0007"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1163\/156855312X626343"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8239539"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1990.126262"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/37.120448"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759557"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2007.906248"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibtech.2013.03.002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1642051"},{"key":"ref10","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref40","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref11","article-title":"Epopt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2016"},{"key":"ref12","article-title":"Attend, adapt and transfer: Attentive deep architecture for adaptive transfer from multiple sources in the same domain","author":"rajendran","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref13","article-title":"A compact, cable-driven, activatable soft wrist with six degrees of freedom for assembly tasks","author":"von drigalski","year":"2020","journal-title":"International Conference on Intelligent Robots and Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197327"},{"key":"ref15","article-title":"Compare contact model-based control and contact model-free learning: A survey of robotic peg-in-hole assembly strategies","author":"xu","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460696"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.074"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1038\/nature14543","article-title":"Design, fabrication and control of soft robots","volume":"521","author":"rus","year":"2015","journal-title":"Nature"},{"key":"ref4","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","first-page":"9728","article-title":"Meta-reinforcement learning for robotic industrial insertion tasks","author":"schoettler","year":"2020","journal-title":"International Conference on Intelligent Robots and Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/430"},{"key":"ref6","article-title":"Measuring the distance between finite markov decision processes","author":"song","year":"2016","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/anie.201006464"},{"key":"ref5","first-page":"408","article-title":"Robots assembling machines: learning from the world robot summit 2018 assembly challenge","volume":"34","author":"von drigalski","year":"2020","journal-title":"Advanced Robotics"},{"key":"ref8","article-title":"Policy transfer with strategy optimization","author":"yu","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/511"},{"key":"ref2","first-page":"9333","article-title":"Hardware conditioned policies for multi-robot transfer learning","author":"chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref9","article-title":"Meta-learning: A survey","author":"vanschoren","year":"2018"},{"key":"ref46","article-title":"Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning","author":"julian","year":"2020"},{"key":"ref20","first-page":"34","article-title":"Improving pilco with bayesian neural network dynamics models","volume":"4","author":"gal","year":"2016","journal-title":"Data-Efficient Machine Learning workshop"},{"key":"ref45","article-title":"Continual learning for robotics","author":"lesort","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref21","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Box2d","year":"0"},{"key":"ref24","first-page":"1332","article-title":"Sample efficient reinforcement learning with gaussian processes","author":"grande","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/B978-0-444-53859-8.00003-5","article-title":"The cross-entropy method for optimization","volume":"31","author":"botev","year":"2013","journal-title":"Handbook of Statistics"},{"key":"ref23","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref26","article-title":"Model-based reinforcement learning via meta-policy optimization","author":"clavera","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref43","article-title":"Moveit","year":"0"},{"key":"ref25","first-page":"642","article-title":"Meta reinforcement learning with latent variable gaussian processes","volume":"34","author":"s\u00e6mundsson","year":"2018","journal-title":"Conference on Uncertainty in Artificial Intelligence"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561081.pdf?arnumber=9561081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T19:21:49Z","timestamp":1659468109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561081","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}