{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:57:22Z","timestamp":1730195842720,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1109\/amc.2019.8371085","type":"proceedings-article","created":{"date-parts":[[2018,6,21]],"date-time":"2018-06-21T20:11:22Z","timestamp":1529611882000},"page":"187-192","source":"Crossref","is-referenced-by-count":1,"title":["Optimal routing control of a construction machine by deep reinforcement learning"],"prefix":"10.1109","author":[{"given":"Zeyuan","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayuki","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutaka","family":"Uchimura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Asynchronous Methods for Deep Reinforcement learning","author":"volodymyr","year":"2016","journal-title":"arXiv 1602 01783v2 [cs LG]"},{"key":"ref11","article-title":"Rainbow: Combining Improvements in Deep Reinforcement learning","author":"matteo","year":"2017","journal-title":"arXiv 1710 02298v1 [cs AI]"},{"key":"ref12","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","volume":"37","author":"sergey","year":"2015","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"journal-title":"Learning form Delayed Rewards","year":"1989","author":"watkins","key":"ref13"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Technical Note Q-learning","volume":"8","author":"christopher","year":"1992","journal-title":"Machine Learning"},{"key":"ref15","first-page":"1","article-title":"Learning Rates for Q-learning","volume":"5","author":"eyal","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","article-title":"To Discount or not to Discount in Reinforcement Learning: A Case Study Comparing R learning and Q learning","author":"sridhar","year":"1994","journal-title":"Machine Learning Proceedings of the Eleventh International Conference"},{"key":"ref17","first-page":"2","article-title":"Routing Control of Construction machine Based on Deep Reinforcement Learning","author":"zeyuan","year":"2017","journal-title":"2017 IEE-Japan Industry Applications Society Conference"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"timothy","year":"2016","journal-title":"arXiv 1509 02971v5 cs LG"},{"key":"ref19","article-title":"Weight Normalization: A Simple Repa-rameterization to Accelerate Training of Deep Neural Networks","author":"tim","year":"2016","journal-title":"arXiv 1602 07868v3 cs LG"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00077-0"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"david","year":"2016","journal-title":"Nature"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Humae level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","article-title":"Deep Reinforcement learning with Double Q-learning","author":"hasselt","year":"2015","journal-title":"arXiv 1509 06461v3 cs LG"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"david","year":"2017","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01501508"},{"key":"ref1","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Dueling Network Architectures for Deep Reinforcement learning","author":"ziyu","year":"2016","journal-title":"arXiv 1511 06581v3 cs LG"}],"event":{"name":"2018 15th International Workshop on Advanced Motion Control (AMC)","start":{"date-parts":[[2018,3,9]]},"location":"Tokyo","end":{"date-parts":[[2018,3,11]]}},"container-title":["2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8369063\/8371050\/08371085.pdf?arnumber=8371085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:41:31Z","timestamp":1598229691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8371085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/amc.2019.8371085","relation":{},"subject":[],"published":{"date-parts":[[2018,3]]}}}