Automatic Policy Synthesis to Improve the Safety of Nonlinear Dynamical Systems

by   Arash Mehrjou, et al.

Learning controllers merely based on a performance metric has been proven effective in many physical and non-physical tasks in both control theory and reinforcement learning. However, in practice, the controller must guarantee some notion of safety to ensure that it does not harm either the agent or the environment. Stability is a crucial notion of safety, whose violation can certainly cause unsafe behaviors. Lyapunov functions are effective tools to assess stability in nonlinear dynamical systems. In this paper, we combine an improving Lyapunov function with automatic controller synthesis to obtain control policies with large safe regions. We propose a two-player collaborative algorithm that alternates between estimating a Lyapunov function and deriving a controller that gradually enlarges the stability region of the closed-loop system. We provide theoretical results on the class of systems that can be treated with the proposed algorithm and empirically evaluate the effectiveness of our method using an exemplary dynamical system.



There are no comments yet.


page 23

page 24


Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics

This paper proposes a framework for safe reinforcement learning that can...

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families

The correspondence between residual networks and dynamical systems motiv...

Synthesis of Feedback Controller for Nonlinear Control Systems with Optimal Region of Attraction

The problem of computing and characterizing Region of Attraction (ROA) w...

Stability-certified reinforcement learning: A control-theoretic perspective

We investigate the important problem of certifying stability of reinforc...

Reinforcement Learning Control of Constrained Dynamic Systems with Uniformly Ultimate Boundedness Stability Guarantee

Reinforcement learning (RL) is promising for complicated stochastic nonl...

Learning Expected Reward for Switched Linear Control Systems: A Non-Asymptotic View

In this work, we show existence of invariant ergodic measure for switche...

ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions

Sample-based learning model predictive control (LMPC) strategies have re...

Code Repositories


Contains the code for the paper Neural Lyapunov Redesign published at L4DC 2021.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.