Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems

Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity. Stability is a crucial property for safety-critical dynamical systems, while stabilization of partially observed many cases, requires retain process long-term memories the past. We consider important class recurrent neural networks (RNN) as dynamic nonlinear uncertain partially-observed derive convex stability conditions based on integral quadratic constraints, S-lemma sequential convexification. To ensure during learning process, we propose projected policy gradient method that iteratively enforces reparametrized space taking advantage mild additional information system dynamics. Numerical experiments show our learns stabilizing with fewer samples achieves higher final performance compared gradient.