Learning Constrained Adaptive Differentiable Predictive Control Policies With Guarantees. (arXiv:2004.11184v6 [eess.SY] UPDATED)

Web: http://arxiv.org/abs/2004.11184

We present differentiable predictive control (DPC), a method for learning
constrained neural control policies for linear systems with probabilistic
performance guarantees. We employ automatic differentiation to obtain direct
policy gradients by backpropagating the model predictive control (MPC) loss
function and constraints penalties through a differentiable closed-loop system
dynamics model. We demonstrate that the proposed method can learn parametric
constrained control policies to stabilize systems with unstable dynamics, track
time-varying references, and satisfy nonlinear state and input constraints. In
contrast with …

arxiv learning predictive