{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T13:52:03Z","timestamp":1725717123216},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T00:00:00Z","timestamp":1670112000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T00:00:00Z","timestamp":1670112000000},"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":[[2022,12,4]]},"DOI":"10.1109\/ssci51031.2022.10022229","type":"proceedings-article","created":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T20:05:39Z","timestamp":1675109139000},"page":"867-874","source":"Crossref","is-referenced-by-count":0,"title":["On Neural Consolidation for Transfer in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Valentin","family":"Guillet","sequence":"first","affiliation":[{"name":"Université de Toulouse,ISAE-Supaero,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dennis","family":"Wilson","sequence":"additional","affiliation":[{"name":"Université de Toulouse,ISAE-Supaero,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Aguilar-Melchor","sequence":"additional","affiliation":[{"name":"SandboxAQ,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanuel","family":"Rachelson","sequence":"additional","affiliation":[{"name":"Université de Toulouse,ISAE-Supaero,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","article-title":"Direct transfer of learned information among neural networks","author":"Pratt","year":"1991","journal-title":"AAAI"},{"key":"ref3","article-title":"Transfer Learning for Rein-forcement Learning Domains: A Survey","author":"Taylor","year":"2009","journal-title":"Journal of ML Research"},{"key":"ref4","article-title":"Policy Distillation","author":"Rusu","year":"2016","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref6","article-title":"Distilling the Knowledge in a Neural Network","volume-title":"NeurIPS Deep Learning Workshop","author":"Hinton","year":"2014"},{"key":"ref7","article-title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","author":"Parisotto","year":"2016","journal-title":"ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.102.3.419"},{"key":"ref9","article-title":"Less-forgetting learning in deep neural networks","author":"Jung","year":"2016","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Distral: Robust multitask reinforcement learning","author":"Teh","year":"2017","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref12","article-title":"Lifelong Learning with Dynamically Expandable Networks","author":"Yoon","year":"2018","journal-title":"ICLR"},{"key":"ref13","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Pathnet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref17","article-title":"Continual Learning Through Synaptic Intelligence","author":"Zenke","year":"2017","journal-title":"ICML"},{"key":"ref18","article-title":"Gradient episodic memory for continual learning","author":"Lopez-Paz","year":"2017","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref20","article-title":"Model Based Reinforcement Learning for Atari","author":"Kaiser","year":"2020","journal-title":"ICLR"},{"key":"ref21","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Continual learning with deep generative replay","author":"Shin","year":"2017","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Progressive reinforcement learning with distillation for multi-skilled motion control","author":"Berseth","year":"2018","journal-title":"ICLR"},{"key":"ref24","article-title":"Progress & compress: A scalable framework for continual learning","author":"Schwarz","year":"2018","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.10.011"},{"key":"ref26","article-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","author":"Finn","year":"2017","journal-title":"ICML"},{"key":"ref27","article-title":"Learning to Continually Learn","author":"Beaulieu","year":"2020","journal-title":"ECAI"},{"key":"ref28","article-title":"Task Agnostic Continual Learning via Meta Learning","volume-title":"ICML Workshop on LifelongML","author":"He","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.29007\/vdxr"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref32","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref34","article-title":"Gradient surgery for multi-task learning","author":"Yu","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2022,12,4]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,7]]}},"container-title":["2022 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022049\/10022014\/10022229.pdf?arnumber=10022229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:44:27Z","timestamp":1707806667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ssci51031.2022.10022229","relation":{},"subject":[],"published":{"date-parts":[[2022,12,4]]}}}