{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:17:37Z","timestamp":1789672657860,"version":"4.0.1"},"reference-count":30,"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\/iros40897.2019.8967908","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"1688-1695","source":"Crossref","is-referenced-by-count":28,"title":["Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems"],"prefix":"10.1109","author":[{"given":"Boyi","family":"Liu","sequence":"first","affiliation":[{"name":"Cloud Computing Lab of Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lujia","family":"Wang","sequence":"additional","affiliation":[{"name":"Cloud Computing Lab of Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of ECE"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2408634"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref11","first-page":"1312","article-title":"Universal Value Function Approximators","author":"schaul","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.004"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2200\/S00832ED1V01Y201802AIM037"},{"key":"ref17","article-title":"Policy Distillation","author":"rusu","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","first-page":"1206","article-title":"Online Multi-Task Learning for Policy Gradient Methods","author":"ammar","year":"2014","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref19","article-title":"Progressive Neural Networks","author":"rusu","year":"2016","journal-title":"Neural Information Processing Systems (NIPS) Conference"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.941632"},{"key":"ref4","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref27","article-title":"Cloud-enabled Robots","author":"kuffner","year":"2010","journal-title":"Humanoid Robots IEEE International Conference on"},{"key":"ref3","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref29","first-page":"171","article-title":"Design and Implementation of VOD (Video on Demand) SaaS Framework for Android Platform on Cloud Environment","author":"srinivasan","year":"2013","journal-title":"IEEE International Conference on Mobile Data Management"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref8","article-title":"Neural SLAM: Learning to Explore with External Memory","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1706 09520"},{"key":"ref7","article-title":"Learning to Navigate in Complex Environments","author":"mirowski","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2376492"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref1","article-title":"Deep Reinforcement Learning","author":"li","year":"2018","journal-title":"arXiv preprint arXiv 1810 10053"},{"key":"ref20","first-page":"316","article-title":"PAC-inspired Option Discovery in Lifelong Reinforcement Learning","author":"brunskill","year":"2014","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref22","article-title":"Federated Learning of Deep Networks using Model Averaging","author":"mcmahan","year":"2016","journal-title":"arXiv preprint arXiv 1602 05629"},{"key":"ref21","first-page":"1553","article-title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","volume":"3","author":"tessler","year":"2017","journal-title":"AAAI"},{"key":"ref24","article-title":"Federated Learning for Mobile Keyboard Prediction","author":"hard","year":"2018","journal-title":"arXiv preprint arXiv 1811 03604"},{"key":"ref23","first-page":"1","article-title":"Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks","author":"nasr","year":"2018","journal-title":"IEEE Symposium on Security and Privacy"},{"key":"ref26","article-title":"Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications","author":"samarakoon","year":"2018","journal-title":"arXiv preprint arXiv 1807 08127"},{"key":"ref25","article-title":"InEdge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning","author":"wang","year":"2018","journal-title":"arXiv preprint arXiv 1809 07857"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"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\/08967908.pdf?arnumber=8967908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:08:26Z","timestamp":1757095706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967908","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}