Learning Deep Stochastic Optimal Control Policies using Forward-Backward SDEs
This addresses decision-making under uncertainty for robotics and autonomy, though it appears incremental as it combines existing theoretical frameworks with neural networks.
The authors tackled stochastic optimal control problems by developing a new methodology based on forward-backward stochastic differential equations and deep neural networks, achieving scalable performance in simulations of three nonlinear systems with and without control constraints.
In this paper we propose a new methodology for decision-making under uncertainty using recent advancements in the areas of nonlinear stochastic optimal control theory, applied mathematics, and machine learning. Grounded on the fundamental relation between certain nonlinear partial differential equations and forward-backward stochastic differential equations, we develop a control framework that is scalable and applicable to general classes of stochastic systems and decision-making problem formulations in robotics and autonomy. The proposed deep neural network architectures for stochastic control consist of recurrent and fully connected layers. The performance and scalability of the aforementioned algorithm are investigated in three non-linear systems in simulation with and without control constraints. We conclude with a discussion on future directions and their implications to robotics.