{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:07:31Z","timestamp":1781622451372,"version":"3.54.5"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/icarcv.2018.8581309","type":"proceedings-article","created":{"date-parts":[[2019,1,9]],"date-time":"2019-01-09T18:57:00Z","timestamp":1547060220000},"page":"311-318","source":"Crossref","is-referenced-by-count":16,"title":["Recurrent Deterministic Policy Gradient Method for Bipedal Locomotion on Rough Terrain Challenge"],"prefix":"10.1109","author":[{"given":"Doo Re","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"McGreavy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","author":"rusu","year":"2015","journal-title":"Policy distillation"},{"key":"ref31","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref30","author":"zhang","year":"2017","journal-title":"A deeper look at experience replay"},{"key":"ref10","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref11","author":"heess","year":"2015","journal-title":"Memory-based control with recurrent neural networks"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML-14)"},{"key":"ref14","author":"heess","year":"2017","journal-title":"Emergence of locomotion behaviours in rich environments"},{"key":"ref15","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"Point-based pomdp algorithms: Improved analysis and implementation","author":"smith","year":"2005","journal-title":"UAI"},{"key":"ref17","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref18","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref19","article-title":"Parameter space noise for exploration","author":"plappert","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref28","first-page":"2140","article-title":"Playing fps games with deep reinforcement learning","author":"lample","year":"2017","journal-title":"AAAI"},{"key":"ref4","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"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref3","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/3072959.3073602","article-title":"Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning","volume":"36","author":"peng","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref29","author":"ollivier","year":"2015","journal-title":"Training recurrent networks online without backtracking"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2766910"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.5.1071"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246900"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307522"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1093\/jigpal\/jzp049","article-title":"Recurrent policy gradients","volume":"18","author":"wierstra","year":"2009","journal-title":"Logic Journal of IGPL"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref22","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref21","volume":"abs 1507 6527","author":"hausknecht","year":"2015","journal-title":"Deep recurrent q-learning for partially observable mdps"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref23","author":"harb","year":"2017","journal-title":"Investigating recurrence and eligibility traces in deep q-networks"},{"key":"ref26","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref25","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"}],"event":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","location":"Singapore","start":{"date-parts":[[2018,11,18]]},"end":{"date-parts":[[2018,11,21]]}},"container-title":["2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8564369\/8580630\/08581309.pdf?arnumber=8581309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:46:25Z","timestamp":1598233585000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8581309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icarcv.2018.8581309","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}