{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:23:02Z","timestamp":1730265782675,"version":"3.28.0"},"reference-count":25,"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.2019.8852019","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Strategy Selection in Complex Game Environments Based on Transfer Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Hongwei","family":"Ge","sequence":"first","affiliation":[]},{"given":"Mingde","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Sun","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"mnih","key":"ref10"},{"key":"ref11","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref14","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: a survey","volume":"10","author":"tayor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","article-title":"Actor-Mimic: Deep deep multi-task and transfer reinforcement learning","author":"parisotto","year":"2016","journal-title":"International Conference on Learning Reresentions"},{"article-title":"Progressive neural networks","year":"2016","author":"rusu","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.898"},{"key":"ref18","first-page":"640","article-title":"Is Learning the n-th Thing Any Easier than the First?","volume":"8","author":"thrun","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114730"},{"key":"ref4","article-title":"Improving elevator performance using reinforcement learning","author":"crites","year":"1995","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref3","first-page":"98","article-title":"Autonomous Learning of Stable Quadruped Locomotion","author":"saggar","year":"2006","journal-title":"RoboCup 2006 Robot Soccer World Cup X"},{"article-title":"Evolution strategies as a scalable alternative to reinforcement learning","year":"2017","author":"salimans","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"article-title":"Playing Atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-018-0147-8"},{"key":"ref2","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":"ref9","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2690910"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2664665"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2607018"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref24"},{"key":"ref23","article-title":"Network in network","author":"lin","year":"2013","journal-title":"International Conference on Learning Representations"},{"article-title":"Reinforcement learning with unsupervised auxiliary tasks","year":"2016","author":"jaderberg","key":"ref25"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","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\/08852019.pdf?arnumber=8852019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:53:51Z","timestamp":1658094831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852019","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}