{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:31:30Z","timestamp":1773246690448,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/robosoft60065.2024.10522027","type":"proceedings-article","created":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T17:23:35Z","timestamp":1715621015000},"page":"1026-1033","source":"Crossref","is-referenced-by-count":8,"title":["Continual Policy Distillation of Reinforcement Learning-based Controllers for Soft Robotic In-Hand Manipulation"],"prefix":"10.1109","author":[{"given":"Lanpei","family":"Li","sequence":"first","affiliation":[{"name":"University of Pisa,Department of Computer Science,Pisa,Italy,56127"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrico","family":"Donato","sequence":"additional","affiliation":[{"name":"The BioRobotics Institute, Sant’ Anna School of Advanced Studies,Pontedera (PI),Italy,56025"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincenzo","family":"Lomonaco","sequence":"additional","affiliation":[{"name":"University of Pisa,Department of Computer Science,Pisa,Italy,56127"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Egidio","family":"Falotico","sequence":"additional","affiliation":[{"name":"The BioRobotics Institute, Sant’ Anna School of Advanced Studies,Pontedera (PI),Italy,56025"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8414"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29041-1_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201707035"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2016.2551557"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3156806"},{"issue":"1","key":"ref7","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"The Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.07.021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2023.3253421"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/s23198278"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146903"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2023.3310865"},{"key":"ref14","article-title":"To enabling plant-like movement capabilities in continuum arms","volume-title":"2022 I-RIM Conference","author":"Donato"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/RoboSoft55895.2023.10122017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2878318"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.861825"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref19","volume-title":"Policy distillation","author":"Rusu","year":"2016"},{"key":"ref20","article-title":"Droid: Learning from offline heterogeneous demonstrations via reward-policy distillation","volume-title":"2023 Conference on Robot Learning","author":"Jayanthi"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3157369"},{"key":"ref22","article-title":"Discorl: Continual reinforcement learning via policy distillation","author":"Traor\u00e9","year":"2019","journal-title":"arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636059"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3149580"},{"key":"ref25","volume-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2020"},{"issue":"268","key":"ref26","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00399"},{"key":"ref28","article-title":"Three scenarios for continual learning","author":"van de Ven","year":"2019","journal-title":"arXiv"},{"key":"ref29","article-title":"On tiny episodic memories in continual learning","author":"Chaudhry","year":"2019","journal-title":"arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00424"}],"event":{"name":"2024 IEEE 7th International Conference on Soft Robotics (RoboSoft)","location":"San Diego, CA, USA","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,17]]}},"container-title":["2024 IEEE 7th International Conference on Soft Robotics (RoboSoft)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10521892\/10521893\/10522027.pdf?arnumber=10522027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T18:16:38Z","timestamp":1732731398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10522027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/robosoft60065.2024.10522027","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}