Statistical learning theory for control: A finite-sample perspective
Learning algorithms have become an integral component to modern engineering solutions.
Examples range from self-driving cars and recommender systems to finance and even …
Examples range from self-driving cars and recommender systems to finance and even …
Regret analysis of learning-based linear quadratic gaussian control with additive exploration
In this paper, we analyze the regret incurred by a computationally efficient exploration
strategy, known as naive exploration, for controlling unknown partially observable systems …
strategy, known as naive exploration, for controlling unknown partially observable systems …
E2-RTO: An Exploitation-Exploration Approach for Real Time Optimization
M Pasquini, H Hjalmarsson - IFAC-PapersOnLine, 2023 - Elsevier
Abstract In Real-Time Optimization, the problem of optimizing the operating conditions of a
plant is solved through iterative methods that directly use plant measurements. In this paper …
plant is solved through iterative methods that directly use plant measurements. In this paper …
Finite-Time Regret Minimization for Linear Quadratic Adaptive Controllers: an experiment design approach
We tackle the problem of finite-time regret minimization in linear quadratic adaptive control.
Regret minimization is a scientific field in both adaptive control and reinforcement learning …
Regret minimization is a scientific field in both adaptive control and reinforcement learning …