@inproceedings{68e3706c2238455d8f5e9f3b77df3513,
title = "Logarithmic regret for learning linear quadratic regulators efficiently",
abstract = "We consider the problem of learning in Linear Quadratic Control systems whose transition parameters are initially unknown. Recent results in this setting have demonstrated efficient learning algorithms with regret growing with the square root of the number of decision steps. We present new efficient algorithms that achieve, perhaps surprisingly, regret that scales only (poly)logarithmically with the number of steps in two scenarios: when only the state transition matrix A is unknown, and when only the stateaction transition matrix B is unknown and the optimal policy satisfies a certain non-degeneracy condition. On the other hand, we give a lower bound that shows that when the latter condition is violated, square root regret is unavoidable.",
author = "Asaf Cassel and Alon Cohen and Tomer Koren",
note = "Publisher Copyright: {\textcopyright} 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.; 37th International Conference on Machine Learning, ICML 2020 ; Conference date: 13-07-2020 Through 18-07-2020",
year = "2020",
language = "الإنجليزيّة",
series = "37th International Conference on Machine Learning, ICML 2020",
pages = "1305--1314",
editor = "Hal Daume and Aarti Singh",
booktitle = "37th International Conference on Machine Learning, ICML 2020",
}