{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:16:52Z","timestamp":1759331812316,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/case48305.2020.9216782","type":"proceedings-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T20:01:51Z","timestamp":1602187311000},"page":"1122-1128","source":"Crossref","is-referenced-by-count":2,"title":["Developmentally Synthesizing Earthworm-Like Locomotion Gaits with Bayesian-Augmented Deep Deterministic Policy Gradients (DDPG)"],"prefix":"10.1109","author":[{"given":"Sayyed Jaffar Ali","family":"Raza","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Apan","family":"Dastider","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"457","article-title":"Bayesian policy gradient algorithms","author":"ghavamzadeh","year":"2007","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/s10994-016-5547-y"},{"key":"ref12","article-title":"Policy distillation","author":"rusu","year":"2015","journal-title":"arXiv preprint arXiv 1511 06295"},{"key":"ref13","first-page":"1510","article-title":"Learning deep latent gaussian models with markov chain monte carlo","volume":"70","author":"hoffman","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/BF00114726"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1145\/1273496.1273534"},{"key":"ref16","article-title":"Bayesian policy search with policy priors","author":"wingate","year":"2011","journal-title":"Twenty-Second International Joint Conference on Artificial Intelligence"},{"key":"ref17","first-page":"1025","article-title":"Efficient bayes-adaptive reinforcement learning using sample-based search","author":"guez","year":"2012","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TAC.2009.2012975"},{"year":"1992","author":"thrun","article-title":"Efficient exploration in reinforcement learning","key":"ref19"},{"year":"2016","author":"alshamsi","article-title":"Development of a local prosthetic limb using artificial intelligence","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1177\/0278364919881687"},{"key":"ref6","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":"ref5","DOI":"10.1073\/pnas.1610706114"},{"key":"ref8","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"4th International Conference on Learning Representations (ICLR 2016)"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICRA.2017.7989385"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/s11044-014-9428-5"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.5430\/air.v2n1p12"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/IROS40897.2019.8968010"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ROBOT.1996.506885"}],"event":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2020,8,20]]},"location":"Hong Kong, Hong Kong","end":{"date-parts":[[2020,8,21]]}},"container-title":["2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9210430\/9216730\/09216782.pdf?arnumber=9216782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T16:00:20Z","timestamp":1656345620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9216782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/case48305.2020.9216782","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}