On the stability analysis of optimal state feedbacks as represented by deep neural models

by   Dario Izzo, et al.

Research has shown how the optimal feedback control of several non linear systems of interest in aerospace applications can be represented by deep neural architectures and trained using techniques including imitation learning, reinforcement learning and evolutionary algorithms. Such deep architectures are here also referred to as Guidance and Control Networks, or G&CNETs. It is difficult to provide theoretical proofs on the control stability of such neural control architectures in general, and G&CNETs in particular, to perturbations, time delays or model uncertainties or to compute stability margins and trace them back to the network training process or to its architecture. In most cases the analysis of the trained network is performed via Monte Carlo experiments and practitioners renounce to any formal guarantee. This lack of validation naturally leads to skepticism especially in cases where safety and validation are of paramount importance such as is the case, for example, in the automotive or space industry. In an attempt to narrow the gap between deep learning research and control theory, we propose a new methodology based on differntal algebra and automated differentiation to obtain formal guarantees on the behaviour of neural based control sysetems.


page 1

page 2

page 3

page 4


Stability Guarantees for Continuous RL Control

Lack of stability guarantees strongly limits the use of reinforcement le...

Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods

Learning-enabled control systems have demonstrated impressive empirical ...

Neuroevolution of Recurrent Architectures on Control Tasks

Modern artificial intelligence works typically train the parameters of f...

Learning the optimal state-feedback via supervised imitation learning

Imitation learning is a control design paradigm that seeks to learn a co...

Martingale Functional Control variates via Deep Learning

We propose black-box-type control variate for Monte Carlo simulations by...

Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees

We study the problem of learning controllers for discrete-time non-linea...

Optimal Machine Intelligence Near the Edge of Chaos

It has long been suggested that living systems, in particular the brain,...

Please sign up or login with your details

Forgot password? Click here to reset