A Decoupled Data Based Approach to Stochastic Optimal Control Problems
This work addresses the challenge of stochastic optimal control for systems with unknown dynamics, offering a practical decoupled approach that leverages existing NLP solvers and data-driven LQR design.
The paper proposes a decoupled data-based control (D2C) approach for stochastic optimal control with unknown dynamics, achieving near-optimal performance by combining open-loop trajectory optimization with a learned LQR controller. The method is demonstrated on three benchmark problems.
This paper studies the stochastic optimal control problem for systems with unknown dynamics. A novel decoupled data based control (D2C) approach is proposed, which solves the problem in a decoupled "open loop-closed loop" fashion that is shown to be near-optimal. First, an open-loop deterministic trajectory optimization problem is solved using a black-box simulation model of the dynamical system using a standard nonlinear programming (NLP) solver. Then a Linear Quadratic Regulator (LQR) controller is designed for the nominal trajectory-dependent linearized system which is learned using input-output experimental data. Computational examples are used to illustrate the performance of the proposed approach with three benchmark problems.