2012/03/15 by Bart van den Broek, Broek, Bart van den, Wim Wiegerinck +3 · 2 citations
Computer Science · #AI-based Problem Solving and Planning #FOS: Electrical engineering #FOS: Mathematics #Optimization and Control (math.OC) #Reinforcement Learning in Robotics #Robotic Path Planning Algorithms #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1203.3523
openalex publication_date 2012/03/15 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28
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.