{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:41:48Z","timestamp":1730266908705,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651424","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features"],"prefix":"10.1109","author":[{"given":"JaeYoon","family":"Kim","sequence":"first","affiliation":[{"name":"University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyu","family":"Xuan","sequence":"additional","affiliation":[{"name":"University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christy","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney,Visualisation Institute,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farookh","family":"Hussain","sequence":"additional","affiliation":[{"name":"University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6202"},{"article-title":"Variational intrinsic control","year":"2016","author":"Gregor","key":"ref3"},{"article-title":"Diversity is all you need: Learning skills without a reward function","year":"2018","author":"Eysenbach","key":"ref4"},{"article-title":"Variational option discovery algorithms","year":"2018","author":"Achiam","key":"ref5"},{"article-title":"Universal successor features approximators","year":"2018","author":"Borsa","key":"ref6"},{"article-title":"Meta reinforcement learning with successor feature based context","year":"2022","author":"Han","key":"ref7"},{"article-title":"Fast task inference with variational intrinsic successor features","year":"2019","author":"Hansen","key":"ref8"},{"key":"ref9","first-page":"6736","article-title":"Aps: Active pretraining with successor features","volume-title":"International Conference on Machine Learning","author":"Liu"},{"article-title":"Urlb: Unsupervised reinforcement learning benchmark","year":"2021","author":"Laskin","key":"ref10"},{"key":"ref11","first-page":"18459","article-title":"Behavior from the void: Unsupervised active pre-training","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Successor features for transfer in reinforcement learning","year":"2016","author":"Barreto","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"article-title":"Transfer in deep reinforcement learning using successor features and generalised policy improvement","year":"2019","author":"Barreto","key":"ref14"},{"article-title":"Universal successor features for transfer reinforcement learning","year":"2020","author":"Ma","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropsychologia.2018.10.009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007475"},{"article-title":"When should agents explore?","year":"2021","author":"Pislar","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1327"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.60"},{"article-title":"Advantages and limitations of using successor features for transfer in reinforcement learning","year":"2017","author":"Lehnert","key":"ref22"},{"key":"ref23","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International Conference on Machine Learning","author":"Schaul"},{"article-title":"Unsupervised control through non-parametric discriminative rewards","year":"2018","author":"Warde-Farley","key":"ref24"},{"article-title":"Efficient exploration via state marginal matching","year":"2019","author":"Lee","key":"ref25"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651424.pdf?arnumber=10651424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:06:46Z","timestamp":1725955606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651424","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}