{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T13:13:29Z","timestamp":1768742009578,"version":"3.49.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852397","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["Mixing Update Q-value for Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zhunan","family":"Li","sequence":"first","affiliation":[]},{"given":"Xinwen","family":"Hou","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref14","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref4","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume":"80","author":"fujimoto","year":"0"},{"key":"ref3","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref5","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proc 1993 Connectionist Models Summer School Lawrence Erlbaum"},{"key":"ref8","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref7","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref2","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","article-title":"Learning from delayed rewards","author":"watkins","year":"1989","journal-title":"Ph D Dissertation"},{"key":"ref9","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","location":"Budapest, Hungary","start":{"date-parts":[[2019,7,14]]},"end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852397.pdf?arnumber=8852397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:55:41Z","timestamp":1658094941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852397\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852397","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}