{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T12:47:28Z","timestamp":1725626848155},"reference-count":15,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1109\/ccece.2015.7129295","type":"proceedings-article","created":{"date-parts":[[2015,6,26]],"date-time":"2015-06-26T22:04:53Z","timestamp":1435356293000},"page":"314-319","source":"Crossref","is-referenced-by-count":1,"title":["Handling stochastic reward delays in machine reinforcement learning"],"prefix":"10.1109","author":[{"given":"Jeffrey S.","family":"Campbell","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sidney N.","family":"Givigi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Howard M.","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9959-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(03)00167-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref13","article-title":"Multiple Model Q-learning for Stochastic Time-Delayed Reinforcement Learning","author":"campbell","year":"2014","journal-title":"SUBMITTED TO Journal of Intelligent and Robotic Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2316\/Journal.201.2007.3.201-1756"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISECS.2008.102"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967367"},{"key":"ref6","first-page":"2681","article-title":"An application of reinforcement learning to voltage control in power system","author":"guo","year":"2004","journal-title":"Control and Automation 2004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5624977"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.809799"},{"key":"ref7","article-title":"Reinforcement learning: A survey","author":"kaelbling","year":"1996","journal-title":"arXiv preprint cs\/9605103"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118266502.ch1"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref1"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-74958-5_41","article-title":"Planning and learning in environments with delayed feedback","author":"walsh","year":"2007","journal-title":"Machine Learning ECML 2007"}],"event":{"name":"2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE)","start":{"date-parts":[[2015,5,3]]},"location":"Halifax, NS, Canada","end":{"date-parts":[[2015,5,6]]}},"container-title":["2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7120003\/7129089\/07129295.pdf?arnumber=7129295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T14:37:40Z","timestamp":1498228660000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7129295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/ccece.2015.7129295","relation":{},"subject":[],"published":{"date-parts":[[2015,5]]}}}