Input Perturbations for Adaptive Control and Learning
This paper studies adaptive algorithms for simultaneous regulation (i.e., control) and estimation (i.e., learning) of Multiple Input Multiple Output (MIMO) linear dynamical systems. It proposes practical, easy to implement control policies based on perturbations of input signals. Such policies are shown to achieve a worst-case regret that scales as the square-root of the time horizon, and holds uniformly over time. Further, it discusses specific settings where such greedy policies attain the information theoretic lower bound of logarithmic regret. To establish the results, recent advances on self-normalized martingales together with a novel method of policy decomposition are leveraged.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Certified Robust Control under Adversarial Perturbations
Autonomous systems increasingly rely on machine learning techniques to transform high-dimensional raw inputs into predictions that are then used for decision-making and control. However, it is often easy to maliciously m…
Decision MakingBackstepping-based Integral Sliding Mode Control with Time Delay Estimation for Autonomous Underwater Vehicles
The aim of this paper is to propose a high performance control approach for trajectory tracking of Autonomous Underwater Vehicles (AUVs). However, the controller performance can be affected by the unknown perturbations i…
Adaptive Event-triggered Control For Strict-feedback Systems With Time-varying Parameters
In this article, we develop a new adaptive event-triggered asymptotic control scheme for strict-feedback systems with fast time-varying parameters. To deal with time-varying parameters with unknown variation boundaries i…
parameter estimationTowards Robust Neural Networks via Close-loop Control
Despite their success in massive engineering applications, deep neural networks are vulnerable to various perturbations due to their black-box nature. Recent study has shown that a deep neural network can misclassify the…
Antifragility as a complex system's response to perturbations, volatility, and time
Antifragility characterizes the benefit of a dynamical system derived from the variability in environmental perturbations. Antifragility carries a precise definition that quantifies a system's output response to input va…