{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:24:22Z","timestamp":1730265862313,"version":"3.28.0"},"reference-count":24,"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\/ijcnn48605.2020.9207622","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":0,"title":["Improved Stochastic Synapse Reinforcement Learning for Continuous Actions in Sharply Changing Environments"],"prefix":"10.1109","author":[{"given":"Syed Naveed","family":"Hussain Shah","sequence":"first","affiliation":[]},{"given":"Dean","family":"Frederick Hougen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058926"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8285425"},{"key":"ref14","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","first-page":"6","article-title":"Stochastic reinforcement learning for continuous actions in dynamic environments","author":"shah","year":"2020","journal-title":"Florida Artificial Intelligence Research Society (FLAIRS) International Conference"},{"key":"ref16","first-page":"487","article-title":"Rethinking stochasticity in neural networks for reinforcement learning with continuous actions","author":"shah","year":"0","journal-title":"IEEE Symposium Series on Computational Intelligence"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/9780470512517"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.83.051125"},{"key":"ref19","first-page":"393","article-title":"Extending Kohonen’s self-organizing mapping algorithm to learn ballistic movements","volume":"f41","author":"ritter","year":"1987","journal-title":"Neural Computers"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29920-9_21"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.13"},{"key":"ref6","article-title":"Adaptive online learning in dynamic environments","author":"zhang","year":"2018","journal-title":"arXiv 1810 10815v1 [cs LG]"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"ref8","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971 [cs stat]"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0531(70)90038-4"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref9","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"arXiv 1603 00748"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90056-Q"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/2286991"},{"key":"ref21","first-page":"430","article-title":"A randomized ANOVA procedure for comparing performance curves","volume":"98","author":"piater","year":"1998","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8285400"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI44817.2019.9003146"}],"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\/09207622.pdf?arnumber=9207622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:58:34Z","timestamp":1656453514000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9207622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9207622","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}