Risk Sensitive Path Integral Control
Abstract
Recently path integral methods have been developed for stochastic optimal control for a wide class of models with non-linear dynamics in continuous space-time. Path integral methods find the control that minimizes the expected cost-to-go. In this paper we show that under the same assumptions, path integral methods generalize directly to risk sensitive stochastic optimal control. Here the method minimizes in expectation an exponentially weighted cost-to-go. Depending on the exponential weight, risk seeking or risk averse behaviour is obtained. We demonstrate the approach on risk sensitive stochastic optimal control problems beyond the linear-quadratic case, showing the intricate interaction of multi-modal control with risk sensitivity.
Keywords
Cite
@article{arxiv.1203.3523,
title = {Risk Sensitive Path Integral Control},
author = {Bart van den Broek and Wim Wiegerinck and Hilbert Kappen},
journal= {arXiv preprint arXiv:1203.3523},
year = {2012}
}
Comments
Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010)