{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T06:28:36Z","timestamp":1725604116796},"reference-count":12,"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.2019.8848080","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":3,"title":["Action Spaces in Deep Reinforcement Learning to Mimic Human Input Devices"],"prefix":"10.1109","author":[{"given":"Marco","family":"Pleines","sequence":"first","affiliation":[]},{"given":"Frank","family":"Zimmer","sequence":"additional","affiliation":[]},{"given":"Vincent-Pierre","family":"Berges","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Continuous control with deep reinforcement learning","year":"0","author":"lillicrap","key":"ref4"},{"article-title":"Unity: A general platform for intelligent agents","year":"0","author":"juliani","key":"ref3"},{"article-title":"Alphastar: Mastering the real-time strategy game starcraft ii","year":"2019","author":"vinyals","key":"ref10"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref6"},{"article-title":"Emergent complexity via multi-agent competition","year":"2017","author":"bansal","key":"ref11"},{"article-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"mnih","key":"ref5"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2019\/373","article-title":"Obstacle tower: A generalization challenge in vision, control, and planning","author":"juliani","year":"2019"},{"article-title":"Deep reinforcement learning in parameterized action space","year":"2015","author":"hausknecht","key":"ref8"},{"article-title":"Action branching architectures for deep reinforcement learning","year":"2017","author":"tavakoli","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490398"},{"article-title":"Parametrized deep q-networks learning: Reinforcement learning with discrete-continuous hybrid action space","year":"2018","author":"xiong","key":"ref9"},{"year":"2018","key":"ref1","article-title":"Openai five"}],"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\/08848080.pdf?arnumber=8848080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T15:24:19Z","timestamp":1658157859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8848080","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}