Keywords: [ Planning, Control, and Multiagent Learning ] [ Online Learning / Bandits ] [ Boosting / Ensemble Methods ] [ Planning and Control ]
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.