{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T04:41:27Z","timestamp":1729658487231,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1109\/smc.2014.6974146","type":"proceedings-article","created":{"date-parts":[[2014,12,8]],"date-time":"2014-12-08T22:27:18Z","timestamp":1418077638000},"page":"1611-1617","source":"Crossref","is-referenced-by-count":4,"title":["Multiple-model Q-learning for stochastic reinforcement delays"],"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":"10.1109\/TAC.2003.809799"},{"key":"ref11","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"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2316\/Journal.201.2007.3.201-1756"},{"key":"ref13","article-title":"Multiple Model Q-learning for Stochastic Time-Delayed Reinforcement Learning","author":"campbell","year":"2014","journal-title":"Journal of Intelligent & Robotic Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref4","first-page":"2\/1","article-title":"the application of continuous action reinforcement learning automata to adaptive pid tuning","author":"howell","year":"2000","journal-title":"IEE Seminar Learning Systems for Control"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref6","first-page":"30","article-title":"Application of Reinforcement Learning in Autonomous Navigation for Virtual Vehicles","volume":"2","author":"lianqiang","year":"2009","journal-title":"Hybrid Intelligent Systems 2009 HIS '09 Ninth International Conference on"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5624977"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2009.2013272"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/ROBIO.2004.1521772","article-title":"A study of reinforcement learning with knowledge sharing","author":"ito","year":"2004","journal-title":"IEEE International Conference on Robotics and Biomimetics"},{"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","article-title":"Reinforcement learning: A survey","author":"kaelbling","year":"1996","journal-title":"arXiv preprint cs\/9605103"}],"event":{"name":"2014 IEEE International Conference on Systems, Man and Cybernetics - SMC","start":{"date-parts":[[2014,10,5]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2014,10,8]]}},"container-title":["2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6960119\/6973862\/06974146.pdf?arnumber=6974146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T15:19:36Z","timestamp":1602688776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6974146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/smc.2014.6974146","relation":{},"subject":[],"published":{"date-parts":[[2014,10]]}}}