{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:32:32Z","timestamp":1730266352130,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534126","type":"proceedings-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T20:32:37Z","timestamp":1632342757000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Enhanced Cost Per Click via Reinforcement Learning Without Exploration"],"prefix":"10.1109","author":[{"given":"Sinan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep reinforcement learning with double q-learning","volume":"30","author":"van hasselt","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref11","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref13","article-title":"Ladder: A human-level bidding agent for large-scale real-time online auctions","author":"wang","year":"2017","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref15","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"jaques","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref16","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","author":"kumar","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"fujimoto","year":"2019","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1145\/1772690.1772860"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/SOLI.2014.6960761"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/2623330.2623357"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1145\/3292500.3330782"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1145\/2623330.2623633"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/3018661.3018702"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1145\/3097983.3098134"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/IJCNN.2018.8489092"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1007\/978-3-319-55699-4_11"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1038\/nature14236"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/3219819.3219918"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1145\/3269206.3272021"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/3269206.3271748"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534126.pdf?arnumber=9534126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:45:47Z","timestamp":1652197547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534126","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}