{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T20:04:47Z","timestamp":1790712287559,"version":"4.1.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1109\/icra.2016.7487755","type":"proceedings-article","created":{"date-parts":[[2016,6,9]],"date-time":"2016-06-09T21:33:24Z","timestamp":1465508004000},"page":"5434-5441","source":"Crossref","is-referenced-by-count":33,"title":["Neural networks and differential dynamic programming for reinforcement learning problems"],"prefix":"10.1109","author":[{"given":"Akihiko","family":"Yamaguchi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher G.","family":"Atkeson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-013-9328-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9290-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/00207176608921369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/37.257895"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1248926"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967350"},{"key":"ref17","article-title":"Variational policy search via trajectory optimization","volume":"26","author":"levine","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Probabilistic differential dynamic programming","volume":"27","author":"pan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref6","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2015","journal-title":"ArXiv e-prints no arXiv 1504 00702"},{"key":"ref5","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop 2013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843615500309"},{"key":"ref2","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649089"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363430"},{"key":"ref20","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref22","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-4620-6_23"},{"key":"ref24","article-title":"An iterative image registration technique with an application to stereo vision","author":"lucas","year":"1981","journal-title":"The 7th International Joint Conference on Artificial Intelligence (IJCAI'81)"},{"key":"ref23","author":"smith","year":"0","journal-title":"Open Dynamics Engine (ODE)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-32494-1_4"}],"event":{"name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","location":"Stockholm, Sweden","start":{"date-parts":[[2016,5,16]]},"end":{"date-parts":[[2016,5,21]]}},"container-title":["2016 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7478842\/7487087\/07487755.pdf?arnumber=7487755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2016,9,29]],"date-time":"2016-09-29T22:28:27Z","timestamp":1475188107000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7487755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icra.2016.7487755","relation":{},"subject":[],"published":{"date-parts":[[2016,5]]}}}