{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:09:34Z","timestamp":1729634974389,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/cdc.2016.7798399","type":"proceedings-article","created":{"date-parts":[[2017,1,5]],"date-time":"2017-01-05T17:11:18Z","timestamp":1483636278000},"page":"1003-1008","source":"Crossref","is-referenced-by-count":3,"title":["An exact distributed newton method for reinforcement learning"],"prefix":"10.1109","author":[{"given":"Rasul","family":"Tutunov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitham Bou","family":"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","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-0997-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0897-y"},{"key":"ref12","article-title":"Large-Scale Parallel Collaborative Filtering for the Netflix Price","author":"yunhong","year":"2008","journal-title":"Proceedings of the 4th International Conference on Algorithmic Aspects in Information and Management"},{"key":"ref13","article-title":"Network Newton Part I: Algorithm and Convergence","author":"mokhtari","year":"2015","journal-title":"ArXiv e-prints"},{"key":"ref14","article-title":"Network Newton Part II: Convergence Rate and Implementation","author":"mokhtari","year":"2015","journal-title":"ArXiv e-prints"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2293221"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2591796.2591832"},{"key":"ref17","article-title":"Distributed SDDM Solvers: Theory & Applications","author":"tutunov","year":"2015","journal-title":"ArXiv e-prints"},{"key":"ref18","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","author":"sutton","year":"1999","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.3698"},{"key":"ref4","article-title":"A Distributed Newton Method for Network Utility Maximization II: Convergence","author":"erwin","year":"2013","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF01584346"},{"key":"ref6","article-title":"Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multiplies","volume":"3","author":"boyd","year":"2011","journal-title":"Foundations and Trends in Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2161027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783400"},{"key":"ref7","first-page":"5445","article-title":"Distributed Alternating Direction Method of Multiplies","author":"erwin","year":"2012","journal-title":"Proc Conf Decision Control (CDC)"},{"key":"ref2","article-title":"Rate Analysis of Inexact First Order Methods: Applications to Distributed MPC for Network Systems","author":"necoara","year":"2013","journal-title":"ArXiv e-prints"},{"key":"ref9","article-title":"Fast and Flexible ADMM Algorithms for Trend Filtering","author":"ramdas","year":"2014","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref22","article-title":"Applying the Episodic Natural Actor-Critic Architecture to Motor Primitive Learning","author":"peters","year":"2007","journal-title":"Proceedings of European Symposium on Artificial Neural Networks 2007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9631","article-title":"Autonomous Cross-Domain Knowledge Transfer in Lifelong Policy Gradient Reinforcement Learning","author":"bou-ammar","year":"2015","journal-title":"Proceedings of the International Conference on Artificial Intelligence (IJCAI)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref25","article-title":"Linear Time Average Consensus on Fixed Graphs and Implications for Decentralized Optimization and Multi-Agent Control","author":"olschevsky","year":"2014","journal-title":"ArXiv e-prints"}],"event":{"name":"2016 IEEE 55th Conference on Decision and Control (CDC)","start":{"date-parts":[[2016,12,12]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2016,12,14]]}},"container-title":["2016 IEEE 55th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7786694\/7798233\/07798399.pdf?arnumber=7798399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T19:39:31Z","timestamp":1658345971000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7798399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/cdc.2016.7798399","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}