{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T20:39:17Z","timestamp":1758400757793,"version":"3.44.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8967834","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"5079-5085","source":"Crossref","is-referenced-by-count":12,"title":["Sample-efficient Deep Reinforcement Learning with Imaginary Rollouts for Human-Robot Interaction"],"prefix":"10.1109","author":[{"given":"Mohammad","family":"Thabet","sequence":"first","affiliation":[{"name":"University of Manchester,School of Computer Science,United Kingdom"}]},{"given":"Massimiliano","family":"Patacchiola","sequence":"additional","affiliation":[{"name":"University of Edinbrugh,School of Informatics,United Kingdom"}]},{"given":"Angelo","family":"Cangelosi","sequence":"additional","affiliation":[{"name":"University of Manchester,School of Computer Science,United Kingdom"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Dataefficient deep reinforcement learning for dexterous manipulation","author":"popov","year":"2017","journal-title":"arXiv preprint arXiv 1704 03073"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803357"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref12"},{"key":"ref13","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"journal-title":"Mixture density networks","year":"1994","author":"bishop","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.08.003"},{"key":"ref16","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref4","first-page":"195","article-title":"Uncertainty-driven imagination for continuous deep reinforcement learning","author":"kalweit","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref3","first-page":"5690","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"racani\u00e8re","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"feinberg","year":"2018","journal-title":"arXiv preprint arXiv 1803 00101"},{"key":"ref5","first-page":"2455","article-title":"Recurrent world models facilitate policy evolution","author":"ha","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref7","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"buckman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08967834.pdf?arnumber=8967834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:08:25Z","timestamp":1757095705000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967834","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}