{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:20:01Z","timestamp":1729671601452,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":[[2019,8]]},"DOI":"10.1109\/cig.2019.8848041","type":"proceedings-article","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T01:49:14Z","timestamp":1569548954000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Enhancing Rolling Horizon Evolution with Policy and Value Networks"],"prefix":"10.1109","author":[{"given":"Xin","family":"Tong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2017","author":"schulman","article-title":"Proximal policy optimization algorithms","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1162\/neco.2006.18.12.2936"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"14","DOI":"10.2478\/s13230-010-0002-4","article-title":"Exploring parameter space in reinforcement learning","volume":"1","author":"r\u00fcckstiess","year":"2010","journal-title":"Journal of Behavioral Robotics"},{"year":"2018","author":"khadka","article-title":"Evolutionary reinforcement learning","key":"ref13"},{"year":"2018","author":"pourchot","article-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","key":"ref14"},{"key":"ref15","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":"ref16","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"},{"year":"2018","author":"lowrey","article-title":"Plan online, learn offline: Efficient learning and exploration via model- based control","key":"ref17"},{"year":"2018","author":"hafner","article-title":"Learning latent dynamics for planning from pixels","key":"ref18"},{"year":"2019","author":"kaiser","article-title":"Model-based reinforcement learning for Atari","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref3","article-title":"Monte-Carlo tree search: A new framework for game AI","author":"chaslot","year":"2008","journal-title":"AIIDE"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CEC.2017.7969540"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CIG.2017.8080420"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1038\/nature14236"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1609\/aaai.v33i01.33011691"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/978-3-319-55849-3_28"},{"key":"ref9","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1145\/2463372.2463413"},{"year":"2018","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref20"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"year":"2016","author":"hansen","article-title":"The CMA evolution strategy: A tutorial","key":"ref21"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/IROS.2012.6386109"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1201\/9781420036268"},{"key":"ref25","first-page":"1329","article-title":"Bench- marking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2019 IEEE Conference on Games (CoG)","start":{"date-parts":[[2019,8,20]]},"location":"London, United Kingdom","end":{"date-parts":[[2019,8,23]]}},"container-title":["2019 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8844551\/8847948\/08848041.pdf?arnumber=8848041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T01:42:21Z","timestamp":1664502141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8848041","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}