{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:31:54Z","timestamp":1785605514344,"version":"3.56.0"},"reference-count":21,"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.2019.8851690","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":4,"title":["Deep Reinforcement Learning with Dual Targeting Algorithm"],"prefix":"10.1109","author":[{"given":"Naoki","family":"Kodama","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taku","family":"Harada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuteru","family":"Miyazaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00160"},{"key":"ref11","first-page":"1038","article-title":"Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding","volume":"8","author":"sutton","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Efficient Memory-Based Learning for Robot Control","author":"moore","year":"1990","journal-title":"PhD thesis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref14","article-title":"OpenAI Gym","author":"brockman","year":"2016"},{"key":"ref15","article-title":"Continuous Deep Q-Learning with Model-based Acceleration","author":"gu","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.20965\/jaciii.2017.p0849"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00113898"},{"key":"ref19","first-page":"580","article-title":"A theory of profit sharing in reinforcement learning","volume":"9","author":"miyazaki","year":"1994","journal-title":"Transactions of the Japanese Society for Artificial Intelligence"},{"key":"ref4","article-title":"Dueling Network Architectures for Deep Reinforcement Learning","author":"wang","year":"2015"},{"key":"ref3","article-title":"Prioritized Experience Replay","author":"schaul","year":"2015"},{"key":"ref6","article-title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","author":"hessel","year":"2017"},{"key":"ref5","article-title":"A Distributional Perspective on Reinforcement Learning","author":"bellemare","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref7","article-title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","author":"bellemare","year":"2012"},{"key":"ref2","first-page":"2094","article-title":"Deep Reinforcement Learning with Double Q-Learning","volume":"16","author":"van hasselt","year":"2016","journal-title":"Proc of the Thirtieth AAAI Conference on Artificial Intelligence"},{"key":"ref1","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref20","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2014"},{"key":"ref21","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"2016"}],"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\/08851690.pdf?arnumber=8851690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:54:56Z","timestamp":1658094896000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8851690\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8851690","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}