{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:25:46Z","timestamp":1730255146563,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956692","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"2314-2320","source":"Crossref","is-referenced-by-count":1,"title":["Fast Model-based Policy Search for Universal Policy Networks"],"prefix":"10.1109","author":[{"given":"Buddhika Laknath","family":"Semage","sequence":"first","affiliation":[{"name":"Deakin University,Applied Artificial Intelligence Institute,Geelong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thommen","family":"George Karimpanal","sequence":"additional","affiliation":[{"name":"Deakin University,Applied Artificial Intelligence Institute,Geelong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santu","family":"Rana","sequence":"additional","affiliation":[{"name":"Deakin University,Applied Artificial Intelligence Institute,Geelong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Svetha","family":"Venkatesh","sequence":"additional","affiliation":[{"name":"Deakin University,Applied Artificial Intelligence Institute,Geelong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553426"},{"key":"ref32","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","author":"matas","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340780"},{"key":"ref30","first-page":"4931","article-title":"Grounded action transformation for robot learning in simulation","author":"hanna","year":"2017","journal-title":"AAAI"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974685"},{"article-title":"Meta-reinforcement learning robust to distributional shift via model identification and experience relabeling","year":"2020","author":"mendonca","key":"ref36"},{"key":"ref35","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794343"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968053"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_5"},{"article-title":"A tutorial on bayesian optimization","year":"2018","author":"frazier","key":"ref13"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1016\/j.eswa.2018.08.023","article-title":"A flexible transfer learning framework for bayesian optimization with convergence guarantee","volume":"115","author":"joy","year":"2019","journal-title":"Expert Systems with Applications"},{"key":"ref15","article-title":"Openai gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref16","first-page":"5082","article-title":"PHYRE: A new benchmark for physical reasoning","author":"bakhtin","year":"2019","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"article-title":"Policy transfer with strategy optimization","year":"0","author":"yu","key":"ref18"},{"year":"2008","key":"ref19"},{"key":"ref28","first-page":"445","article-title":"Tunenet: One-shot residual tuning for system identification and sim-to-real robot task transfer","author":"allevato","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref4","first-page":"39","article-title":"Humanoid robots learning to walk faster: From the real world to simulation and back","author":"farchy","year":"2013","journal-title":"AAMAS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562091"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143845"},{"article-title":"A compositional Object-Based approach to learning physical dynamics","year":"2016","author":"chang","key":"ref6"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1007\/s10514-020-09925-w","article-title":"Iterative residual tuning for system identification and sim-to-real robot learning","volume":"44","author":"allevato","year":"2020","journal-title":"Autonomous Robots"},{"key":"ref5","first-page":"497","article-title":"Unsupervised learning of latent physical properties using Perception-Prediction networks","author":"zheng","year":"2018","journal-title":"Proceedings of the Thirty-Fourth UAI 2018 Monterey California USA August 6-10 2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.046"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"article-title":"Nist\/sematech e-handbook of statistical methods; chapter 1: Exploratory data analysis","year":"2003","author":"heckert","key":"ref20"},{"article-title":"Pymunk simulator","year":"0","author":"blomqvist","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref23","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/451"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956692.pdf?arnumber=9956692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:04:36Z","timestamp":1671480276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956692\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956692","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}