×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

Application and comparison of evolutionary algorithms in the framework of the problem of reinforcement learning for unstable systems

Abstract

Application and comparison of evolutionary algorithms in the framework of the problem of reinforcement learning for unstable systems

Abuzyarov A.A., Makarov A.A.

Incoming article date: 17.04.2023

The aim of this work is the implementation and comparison of genetic algorithms in the framework of the problem of reinforcement learning for the control of unstable systems. The unstable system will be the CartPole Open AI GYM object, which simulates the balancing of a rod hinged on a cart that moves left and right. The goal is to keep the pole in a vertical position for as long as possible. The control of this object is implemented using two learning methods: the neuroevolutionary algorithm (NEAT) and the multilayer perceptron using genetic algorithms (DEAP).

Keywords: machine learning, non-revolutionary algorithms, genetic algorithms, reinforcement learning, neural networks