{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T11:42:06Z","timestamp":1748691726424,"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.2019.8848127","type":"proceedings-article","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T01:49:14Z","timestamp":1569548954000},"page":"1-7","source":"Crossref","is-referenced-by-count":7,"title":["A Reinforcement Learning Approach To Synthesizing Climbing Movements"],"prefix":"10.1109","author":[{"given":"Kourosh","family":"Naderi","sequence":"first","affiliation":[]},{"given":"Amin","family":"Babadi","sequence":"additional","affiliation":[]},{"given":"Shaghayegh","family":"Roohi","sequence":"additional","affiliation":[]},{"given":"Perttu","family":"Hamalainen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"2017","author":"schulman","article-title":"Proximal policy optimization algorithms","key":"ref10"},{"year":"2018","author":"haarnoja","article-title":"Soft actor-critic algorithms and applications","key":"ref11"},{"year":"2018","author":"h\u00a8am\u00a8al\u00a8ainen","article-title":"PPO-CMA: Proximal policy optimization with covariance matrix adaptation","key":"ref12"},{"year":"2018","author":"abdolmaleki","article-title":"Maximum a posteriori policy optimisation","key":"ref13"},{"year":"2018","author":"abdolmaleki","article-title":"Relative entropy regularized policy iteration","key":"ref14"},{"year":"2018","author":"tassa","article-title":"Deepmind control suite","key":"ref15"},{"year":"2016","author":"brockman","article-title":"Openai gym","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1177\/0278364906063979"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ROBOT.2009.5152553"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1145\/1477926.1477936"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1145\/3083723"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/3197517.3201311"},{"key":"ref6","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"},{"year":"2018","author":"haarnoja","article-title":"Soft actor-critic: Off- policy maximum entropy deep reinforcement learning with a stochastic actor","key":"ref5"},{"year":"2015","author":"lillicrap","article-title":"Continuous control with deep reinforcement learning","key":"ref8"},{"key":"ref7","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":"juliani","article-title":"Unity: A general platform for intelligent agents","key":"ref2"},{"key":"ref9","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref1","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"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/2185520.2185539"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1111\/cgf.13513"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/3072959.3073707"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1145\/3213773"},{"key":"ref23","article-title":"Computational Climbing for Physics- Based Characters","author":"olsen","year":"2014","journal-title":"The ACM SIGGRAPH \/ Eurographics Symposium on Computer Animation (SCA posters)"},{"key":"ref26","article-title":"Relative entropy regularized policy iteration","volume":"abs 1812 2256","author":"abdolmaleki","year":"2018","journal-title":"CoRR"},{"key":"ref25","first-page":"93","article-title":"Computer-aided imagery in sport and exercise: A case study of indoor wall climbing","author":"naderi","year":"2018","journal-title":"Proceedings of Graphics Interface 2018 ser GI 2018 Canadian Human-Computer Communications Society \/ Société canadienne du dialogue humain-machine"}],"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\/08848127.pdf?arnumber=8848127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:47:05Z","timestamp":1658155625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8848127","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}