{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:52:31Z","timestamp":1775065951859,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["TRR 169"],"award-info":[{"award-number":["TRR 169"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534023","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision"],"prefix":"10.1109","author":[{"given":"Julien","family":"Scholz","sequence":"first","affiliation":[]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[]},{"given":"Muhammad Burhan","family":"Hafez","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","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"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015435"},{"key":"ref13","article-title":"Efficient selectivity and backup operators in Monte-Carlo tree search","author":"coulom","year":"2006","journal-title":"Proceedings Computers and Games 2006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref16","article-title":"Deep successor reinforcement learning","author":"kulkarni","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"key":"ref18","first-page":"530","article-title":"Contextual imagined goals for self-supervised robotic learning","author":"nair","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref19","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"ArXiv e-prints"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.033"},{"key":"ref3","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"ebert","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852254"},{"key":"ref8","author":"duvaud","year":"2019","journal-title":"MuZero General Open Reimplementation of MuZero"},{"key":"ref7","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"2016","journal-title":"ArXiv e-prints"},{"key":"ref2","article-title":"Universal planning networks","author":"srinivas","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref1","article-title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","author":"schrittwieser","year":"2019","journal-title":"ArXiv e-prints"},{"key":"ref9","article-title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","volume":"abs 1712 1815","author":"silver","year":"2017","journal-title":"CoRR"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534023.pdf?arnumber=9534023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:02Z","timestamp":1652197562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534023","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}