TY - JOUR
T1 - Bandit linear control
AU - Cassel, Asaf
AU - Koren, Tomer
N1 - Publisher Copyright:
© 2020 Neural information processing systems foundation. All rights reserved.
PY - 2020
Y1 - 2020
N2 - We consider the problem of controlling a known linear dynamical system under stochastic noise, adversarially chosen costs, and bandit feedback. Unlike the full feedback setting where the entire cost function is revealed after each decision, here only the cost incurred by the learner is observed. We present a new and efficient algorithm that, for strongly convex and smooth costs, obtains regret that grows with the square root of the time horizon T. We also give extensions of this result to general convex, possibly non-smooth costs, and to non-stochastic system noise. A key component of our algorithm is a new technique for addressing bandit optimization of loss functions with memory.
AB - We consider the problem of controlling a known linear dynamical system under stochastic noise, adversarially chosen costs, and bandit feedback. Unlike the full feedback setting where the entire cost function is revealed after each decision, here only the cost incurred by the learner is observed. We present a new and efficient algorithm that, for strongly convex and smooth costs, obtains regret that grows with the square root of the time horizon T. We also give extensions of this result to general convex, possibly non-smooth costs, and to non-stochastic system noise. A key component of our algorithm is a new technique for addressing bandit optimization of loss functions with memory.
UR - http://www.scopus.com/inward/record.url?scp=85102550069&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???
AN - SCOPUS:85102550069
SN - 1049-5258
VL - 2020-December
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 34th Conference on Neural Information Processing Systems, NeurIPS 2020
Y2 - 6 December 2020 through 12 December 2020
ER -