{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:09:14Z","timestamp":1761664154724,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9207295","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Stochastic Curiosity Maximizing Exploration"],"prefix":"10.1109","author":[{"given":"Jen-Tzung","family":"Chien","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-Chien","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref30"},{"article-title":"A benchmarking environment for reinforcement learning based task oriented dialogue management","year":"2017","author":"casanueva","key":"ref10"},{"key":"ref11","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12625"},{"article-title":"Temporal credit assignment in reinforcement learning","year":"1985","author":"sutton","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref15","first-page":"1109","article-title":"VIME: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Neural Information Processing Systems"},{"key":"ref16","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.05.002"},{"key":"ref19","first-page":"4055","article-title":"Successor features for transfer in reinforcement learning","author":"barreto","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref28"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1383"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-4006"},{"article-title":"World models","year":"2018","author":"ha","key":"ref6"},{"key":"ref29","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"article-title":"Auto-encoding variational Bayes","year":"2013","author":"kingma","key":"ref5"},{"key":"ref8","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"},{"article-title":"Playing Atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref7"},{"key":"ref2","first-page":"13","article-title":"Deep Bayesian learning and understanding","author":"chien","year":"2018","journal-title":"Proc of International Conference on Computational Linguistics Tutorial Abstracts"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4013"},{"key":"ref1","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","author":"chentanez","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102421"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2161080"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107295360"},{"journal-title":"Source Separation and Machine Learning","year":"2018","author":"chien","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053735"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160280206"},{"article-title":"MINE: mutual information neural estimation","year":"2018","author":"belghazi","key":"ref25"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09207295.pdf?arnumber=9207295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:58:05Z","timestamp":1656453485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9207295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9207295","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}