Boosting for Control of Dynamical Systems
This work addresses performance enhancement in control systems, presenting an incremental improvement through a novel boosting approach.
The paper tackles the problem of improving controller performance for dynamical systems by proposing a boosting framework that aggregates weak controllers into a more accurate one, with empirical evaluation supporting theoretical findings.
We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation on a host of control settings supports our theoretical findings.