{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T22:36:28Z","timestamp":1761863788098},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/humanoids.2017.8246900","type":"proceedings-article","created":{"date-parts":[[2018,1,8]],"date-time":"2018-01-08T17:46:08Z","timestamp":1515433568000},"page":"372-377","source":"Crossref","is-referenced-by-count":11,"title":["Emergence of human-comparable balancing behaviours by deep reinforcement learning"],"prefix":"10.1109","author":[{"given":"Chuanyu","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taku","family":"Komura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925881"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9504-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152434"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5648837"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2010.5723295"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2006.321385"},{"journal-title":"Concrete problems in ai safety","year":"2016","author":"amodei","key":"ref17"},{"key":"ref18","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"journal-title":"Emergence of locomotion behaviours in rich environments","year":"2017","author":"heess","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2629489"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref5","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353489"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.02455"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2766910"},{"journal-title":"Deep Reinforcement Learning in Parameterized Action Space","year":"2015","author":"hausknecht","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3099564.3099567"},{"journal-title":"Learning and transfer of modulated locomotor controllers","year":"2016","author":"heess","key":"ref21"}],"event":{"name":"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)","start":{"date-parts":[[2017,11,15]]},"location":"Birmingham","end":{"date-parts":[[2017,11,17]]}},"container-title":["2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8215882\/8239529\/08246900.pdf?arnumber=8246900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,2,28]],"date-time":"2018-02-28T15:35:32Z","timestamp":1519832132000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8246900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/humanoids.2017.8246900","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}