{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:17:28Z","timestamp":1730279848891,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"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":[[2022,8]]},"DOI":"10.1109\/jcc56315.2022.00008","type":"proceedings-article","created":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T17:02:13Z","timestamp":1664211733000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty Estimation based Intrinsic Reward For Efficient Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Chao","family":"Chen","sequence":"first","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianjiao","family":"Wan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peichang","family":"Shi","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ding","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"yarats","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref32","article-title":"Behavior from the void: Unsupervised active pre-training","volume":"34","author":"liu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref30","article-title":"Urlb: Unsupervised reinforcement learning benchmark","author":"laskin","year":"2021","journal-title":"Deep RL Workshop NeurIPS 2021"},{"key":"ref36","first-page":"6736","article-title":"Aps: Active pretraining with successor features","author":"liu","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref35","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref34","article-title":"Data-efficient reinforcement learning with self-predictive representations","author":"schwarzer","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1006\/ceps.1999.1020"},{"key":"ref13","article-title":"How can we define intrinsic motivation?","author":"oudeyer","year":"2008","journal-title":"the 8th International Conference on Epigenetic Robotics Modeling Cognitive Development in Robotic Systems"},{"key":"ref14","first-page":"1","article-title":"Exploration by random network distillation","author":"burda","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref15","volume":"28","author":"oh","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"2274","volume":"1810","author":"savinov","year":"2018","journal-title":"Arxiv preprint arXiv"},{"key":"ref17","first-page":"2574","article-title":"Ex2: Exploration with exemplar models for deep reinforcement learning","author":"fu","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems ser NIPS’17"},{"key":"ref18","first-page":"6038","volume":"2002","author":"badia","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref19","volume":"405","author":"bernardo","year":"2009","journal-title":"Bayesian Theory"},{"key":"ref28","first-page":"6347","volume":"1707","author":"schulman","year":"2017","journal-title":"Arxiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref27","first-page":"207","article-title":"Deep gaussian processes","author":"damianou","year":"2013","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref29","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref8","first-page":"5062","article-title":"Self-supervised exploration via disagreement","author":"pathak","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref7","article-title":"Sample efficient deep reinforcement learning via uncertainty estimation","author":"mai","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref2","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":"ref9","first-page":"1050","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.1109\/TNN.1998.712192","article-title":"Reinforcement learning: An introduction","volume":"9","author":"sutton","year":"1998","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.08.066"},{"key":"ref22","article-title":"Can you trust your model’s uncertainty? evaluating predictive uncertainty under dataset shift","volume":"32","author":"ovadia","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref24","first-page":"1","article-title":"Ensemble methods in machine learning","author":"dietterich","year":"2000","journal-title":"International Workshop on Multiple Classifier Systems"},{"key":"ref23","first-page":"6131","article-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","author":"lee","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2892416"},{"key":"ref25","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"lakshminarayanan","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 IEEE International Conference on Joint Cloud Computing (JCC)","start":{"date-parts":[[2022,8,15]]},"location":"Fremont, CA, USA","end":{"date-parts":[[2022,8,18]]}},"container-title":["2022 IEEE International Conference on Joint Cloud Computing (JCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897094\/9898078\/09898087.pdf?arnumber=9898087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T16:51:53Z","timestamp":1665766313000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9898087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/jcc56315.2022.00008","relation":{},"subject":[],"published":{"date-parts":[[2022,8]]}}}