{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:31:29Z","timestamp":1730266289409,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/ijcnn.2018.8489712","type":"proceedings-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T18:25:09Z","timestamp":1539973509000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["Accelerating Deep Continuous Reinforcement Learning through Task Simplification"],"prefix":"10.1109","author":[{"given":"Matthias","family":"Kerzel","sequence":"first","affiliation":[]},{"given":"Hadi Beik","family":"Mohammadi","sequence":"additional","affiliation":[]},{"given":"Mohammad Ali","family":"Zamani","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","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":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref13","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329785"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44778-0_18"},{"journal-title":"End-to-end training of deep visuomotor policies","year":"2015","author":"levine","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.infbeh.2013.01.006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1037\/0012-1649.37.4.561"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/cdev.12263"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref3","first-page":"278364917710318","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","author":"levine","year":"2016","journal-title":"The International Journal of Robotics Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"ref7","article-title":"Neural end-to-end self-learning of visuomotor skills by environment interaction","author":"kerzel","year":"2017","journal-title":"International Conference on Artificial Neural Networks (ICANN)"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9320.001.0001","author":"cangelosi","year":"2015","journal-title":"Developmental Robotics From Babies to Robots"},{"key":"ref9","first-page":"2829","article-title":"Continuous deep qlearning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic interference in connectionist networks: The sequential learning problem","volume":"24","author":"mccloskey","year":"1989","journal-title":"Psychology of Learning and Motivation"},{"key":"ref22","article-title":"Tensorflow: Largescale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv preprint arXiv 1603 04467"},{"journal-title":"Keras","year":"2015","author":"chollet","key":"ref21"}],"event":{"name":"2018 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2018,7,8]]},"location":"Rio de Janeiro","end":{"date-parts":[[2018,7,13]]}},"container-title":["2018 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8465565\/8488986\/08489712.pdf?arnumber=8489712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T19:33:13Z","timestamp":1598211193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8489712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2018.8489712","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}