{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T14:09:24Z","timestamp":1725631764004},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"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":[[2019,4]]},"DOI":"10.1109\/codit.2019.8820403","type":"proceedings-article","created":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T01:09:32Z","timestamp":1567472972000},"page":"563-568","source":"Crossref","is-referenced-by-count":4,"title":["Universal Notice Network: Transferable Knowledge Among Agents"],"prefix":"10.1109","author":[{"given":"Mehdi","family":"Mounsif","sequence":"first","affiliation":[]},{"given":"Sebastien","family":"Lengagne","sequence":"additional","affiliation":[]},{"given":"Benoit","family":"Thuilot","sequence":"additional","affiliation":[]},{"given":"Lounis","family":"Adouane","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2020345"},{"key":"ref11","article-title":"Learning Dexterous In-Hand Manipulation","author":"andrychowicz","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref12","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"0","journal-title":"NIPS-W"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275014"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"journal-title":"Chipmunk","year":"2013","author":"scott","key":"ref17"},{"key":"ref18","article-title":"Mastering the game of go with deep neural networks and tree search","author":"silver","year":"2015","journal-title":"Nature J"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","author":"silver","year":"2017","journal-title":"Nature J"},{"key":"ref4","article-title":"A Neural Algorithm of Artistic Style","author":"gatys","year":"2015","journal-title":"ArXiv e-prints"},{"journal-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks[J]","year":"2017","author":"finn","key":"ref3"},{"key":"ref6","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"CoRR"},{"key":"ref5","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"ArXiv e-prints"},{"journal-title":"Pytorch implementations of reinforcement learning algorithms","year":"2018","author":"kostrikov","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref2","article-title":"Impala: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","author":"espeholt","year":"2018","journal-title":"ArXiv e-prints"},{"journal-title":"ArXiv e-prints","year":"2016","author":"beattie","key":"ref1"},{"key":"ref9","article-title":"Continuous control with deep reinforcement learning","author":"lilicrap","year":"2016","journal-title":"ArXiv"},{"journal-title":"Reinforcement Learning An Introduction","year":"2017","author":"sutton","key":"ref20"},{"key":"ref22","article-title":"Emergent complexity via multi-agent competition","author":"trapit","year":"2017","journal-title":"Technical Report arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref24","article-title":"Caml: Fast Context Adaptation via Meta-Learning","author":"zintgraf","year":"2018","journal-title":"ArXiv e-prints"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"volodymyr","key":"ref23"}],"event":{"name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","start":{"date-parts":[[2019,4,23]]},"location":"Paris, France","end":{"date-parts":[[2019,4,26]]}},"container-title":["2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8806019\/8820291\/08820403.pdf?arnumber=8820403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:23:29Z","timestamp":1658262209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8820403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/codit.2019.8820403","relation":{},"subject":[],"published":{"date-parts":[[2019,4]]}}}