{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:20:51Z","timestamp":1730262051751,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iecon.2018.8591189","type":"proceedings-article","created":{"date-parts":[[2019,1,18]],"date-time":"2019-01-18T22:30:15Z","timestamp":1547850615000},"page":"5068-5073","source":"Crossref","is-referenced-by-count":2,"title":["Autonomous Grading Work Using Deep Reinforcement Learning Based Control"],"prefix":"10.1109","author":[{"given":"Masayuki","family":"Nakatani","sequence":"first","affiliation":[]},{"given":"Zeyuan","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yutaka","family":"Uchimura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"volodymyr","key":"ref10"},{"journal-title":"Rainbow Combining Improvements in Deep Reinforcement Learning","year":"2017","author":"matteo","key":"ref11"},{"journal-title":"Learning form Delayed Rewards","year":"1989","author":"watkins","key":"ref12"},{"key":"ref13","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":"ref14","first-page":"1","article-title":"Learning Rates for Q-learning","volume":"5","author":"eyal","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","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"},{"journal-title":"Imagination-Augmented Agents for Deep Reinforcement Learning","year":"2018","author":"weber","key":"ref16"},{"key":"ref17","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"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2016","author":"timothy","key":"ref18"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref6","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":"ref5","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"},{"journal-title":"Deep reinforcement learning with double q-learning","year":"2015","author":"hasselt","key":"ref8"},{"key":"ref7","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop 2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1541\/ieejjia.5.245"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1541\/ieejjia.5.321"},{"journal-title":"Dueling network architectures for deep reinforcement learning","year":"2016","author":"ziyu","key":"ref9"}],"event":{"name":"IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society","start":{"date-parts":[[2018,10,21]]},"location":"Washington, DC","end":{"date-parts":[[2018,10,23]]}},"container-title":["IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8560606\/8591058\/08591189.pdf?arnumber=8591189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T06:09:26Z","timestamp":1598249366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8591189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/iecon.2018.8591189","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}