{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:32:27Z","timestamp":1730266347976,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9207446","type":"proceedings-article","created":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T20:40:33Z","timestamp":1601412033000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["An Improved Minimax-Q Algorithm Based on Generalized Policy Iteration to Solve a Chaser-Invader Game"],"prefix":"10.1109","author":[{"given":"Minsong","family":"Liu","sequence":"first","affiliation":[]},{"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI44817.2019.9003120"},{"key":"ref11","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","volume":"1","author":"littman","year":"2001","journal-title":"ICML"},{"article-title":"Solution of two-player zero-sum game by successive relaxation","year":"2019","author":"diddigi","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835397"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref14"},{"key":"ref15","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":"ref16","article-title":"Minimax value iteration applied to robotic soc-cer","author":"neto","year":"2005","journal-title":"IEEE ICRA 2005 Workshop on Cooperative Robotics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00015"},{"key":"ref18","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":"silver","year":"2016","journal-title":"Nature"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45164-1_13"},{"key":"ref8","first-page":"242","article-title":"Correlated Q-learning","volume":"3","author":"greenwald","year":"2003","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251450"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/WAC.2018.8430409"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727794"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2911900"},{"article-title":"Policy gradient search: Online planning and expert iteration without search trees","year":"2019","author":"anthony","key":"ref20"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09207446.pdf?arnumber=9207446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T17:58:04Z","timestamp":1656439084000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9207446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9207446","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}