{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:22:43Z","timestamp":1740100963787,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1652159"],"award-info":[{"award-number":["1652159"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892778","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty Aware Model Integration on Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Takashi","family":"Nagata","sequence":"first","affiliation":[{"name":"University of California, Irvine,Computer Science,Irvine,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwei","family":"Xing","sequence":"additional","affiliation":[{"name":"University of California, Irvine,Cognitive Sciences,Irvine,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsutomu","family":"Kumazawa","sequence":"additional","affiliation":[{"name":"Software Research Associates, Inc.,Key Technology Laboratory,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emre","family":"Neftci","sequence":"additional","affiliation":[{"name":"University of California, Irvine,Cognitive Sciences,Irvine,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Model-based reinforcement learning for biological sequence design","author":"angermueller","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref11","first-page":"1050","article-title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","author":"gal","year":"2016","journal-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 ICML'16"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref13","article-title":"Proximal Policy Optimization Algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref17"},{"key":"ref18","first-page":"2555","article-title":"Learning Latent Dynamics for Planning from Pixels","author":"hafner","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"ref4","article-title":"Continuous Deep Q-Learning with Model-based Acceleration","volume":"abs 1603 748","author":"gu","year":"2016","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974682"},{"key":"ref3","article-title":"Learning Dexterous In-Hand Manipulation","volume":"abs 1808 177","author":"andrychowicz","year":"2018","journal-title":"CoRR"},{"key":"ref6","article-title":"Model-Based Reinforcement Learning for Atari","volume":"abs 1903 374","author":"kaiser","year":"2019","journal-title":"CoRR"},{"key":"ref5","article-title":"World Models","volume":"abs 1803 10122","author":"ha","year":"2018","journal-title":"CoRR"},{"key":"ref8","first-page":"179","author":"miller","year":"1995","journal-title":"First Results with Dyna an Integrated Architecture for Learning Planning and Reacting"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1203"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v31i1.16011"},{"key":"ref22","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37 ICML'15"},{"key":"ref21","first-page":"4759","article-title":"Deep Reinforcement Learning in a Handful of Trials Using Probabilistic Dynamics Models","author":"chua","year":"2018","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems NIPS'18"},{"key":"ref24","article-title":"Auto-Encoding Variational Bayes","volume":"abs 1312 6114","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref23","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","article-title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","volume":"abs 1902 2476","author":"maddox","year":"2019","journal-title":"CoRR"},{"key":"ref25","article-title":"OpenAI Gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892778.pdf?arnumber=9892778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:57:31Z","timestamp":1667516251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892778","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}