Skip to yearly menu bar Skip to main content


Poster

Boosting for Control of Dynamical Systems

Naman Agarwal · Nataly Brukhim · Elad Hazan · Zhou Lu

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


Abstract:

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.

Chat is not available.