Git Product home page Git Product logo

neural-lyapunov-control's Introduction

Neural-Lyapunov-Control

This repository contains the code for the paper: Neural Lyapunov Control

Requirements

How it works

The framework consists of a learner and a falsifier. The learner minimizes the Lyapunov risk to find parameters in both a control function and a neural Lyapunov function. The falsifier takes the learned control function and the neural Lyapunov function from the learner and checks whether there is a state vector violating the Lyapunov conditions.

A typical procedure is as follows:

  • Define the neural network with random parameters for Lyapunov function and initialize controller’s parameters to the solution of linear quadratic regular
  • Define a controlled dynamical system
  • Set checking conditions for falsifier
  • Start training and verifying
  • Procedure stops when no counterexample is found

The training part updates the parameters by iteratively minimizing the Lyapunov risk, a cost function measures the degree of violation of the Lyapunov conditions and the verifying part periodically searches counterexample state vectors and adds them back to the training set for the next iteration. This procedure provides flexibility to adjust the cost function for learning additional properties of controllers and Lyapunov functions. In examples we add a tuning term to maximize the region of attractions.

Example

neural-lyapunov-control's People

Contributors

yachienchang avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.