{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:27:27Z","timestamp":1730204847638,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/cdc.2017.8263978","type":"proceedings-article","created":{"date-parts":[[2018,1,23]],"date-time":"2018-01-23T20:30:57Z","timestamp":1516739457000},"page":"2254-2259","source":"Crossref","is-referenced-by-count":2,"title":["Distributed lifelong reinforcement learning with sub-linear regret"],"prefix":"10.1109","author":[{"given":"Rasul","family":"Tutunov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julia","family":"El-Zini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitham","family":"Bou-Ammar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Jadbabaie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Online learning in Markov decision processes with adversarially chosen transition probability distributions","volume":"26","author":"abbasi-yadkori","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Reinforcement learning transfer via sparse coding","author":"bou ammar","year":"2012","journal-title":"Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref12","article-title":"ELLA: An Efficient Lifelong Learning Algorithm","author":"ruvolo","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning (ICML)"},{"key":"ref13","article-title":"Online multitask learning for policy gradient methods","author":"ammar","year":"2014","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/1273496.1273624"},{"key":"ref15","article-title":"Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret","author":"bou ammar","year":"2007","journal-title":"Proc 32th Int Conf Machine Learning (ICML)"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref17","first-page":"5445","article-title":"Distributed Alternating Direction Method of Multiplies","author":"erwin","year":"2012","journal-title":"Proc Conf Decision Control (CDC)"},{"key":"ref18","article-title":"Distribute dOptimization and Statistical Learning via the Alternating Direction Method of Multiplies","volume":"3","author":"boyd","year":"2011","journal-title":"Foundations and Trends in Machine Learning"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TAC.2013.2293221"},{"key":"ref4","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: a survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"year":"1998","author":"sutton","journal-title":"Introduction to Reinforcement Learning","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1049\/ic:19960152"},{"key":"ref5","article-title":"Sequential transfer in multi-armed bandit with finite set of models","volume":"26","author":"azar","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"1564","article-title":"Synthetic structure of industrial plastics (Book style with paper title and editor)","volume":"3","author":"young","year":"1964","journal-title":"Plastics"},{"key":"ref7","article-title":"Online multitask learning for policy gradient methods","author":"ammar","year":"2014","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"year":"2010","author":"busoniu","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1007\/s10994-010-5223-6"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1016\/j.neunet.2008.02.003"},{"year":"2015","author":"mokhtari","journal-title":"Network newton-part i Algorithm and convergence","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CDC.2016.7798399"},{"year":"2015","author":"mokhtari","journal-title":"Network newton-part ii Convergence rate and implementation","key":"ref21"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1017\/CBO9780511804441"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1145\/2591796.2591832"},{"year":"2014","author":"olschevsky","journal-title":"Linear Time Average Consensus on Fixed Graphs and Implications for Decentralized Optimization and Multi-Agent Control","key":"ref25"}],"event":{"name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","start":{"date-parts":[[2017,12,12]]},"location":"Melbourne, Australia","end":{"date-parts":[[2017,12,15]]}},"container-title":["2017 IEEE 56th Annual Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8253407\/8263624\/08263978.pdf?arnumber=8263978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,2,28]],"date-time":"2018-02-28T21:59:19Z","timestamp":1519855159000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8263978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/cdc.2017.8263978","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}