Boosting for Control of Dynamical Systems
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:96-103, 2020.
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.