https://github.com/theokanning/jerry-learns

A simulator to learn walking and backflips using neural networks and genetic evolution.
https://github.com/theokanning/jerry-learns

artificial-intelligence genetic-algorithm neural-network rickandmorty simulation

Last synced: about 2 months ago
JSON representation

A simulator to learn walking and backflips using neural networks and genetic evolution.

• Host: GitHub
• URL: https://github.com/theokanning/jerry-learns
• Owner: TheoKanning
• License: gpl-3.0
• Created: 2016-06-12T16:15:35.000Z (over 8 years ago)
• Default Branch: main
• Last Pushed: 2020-06-19T16:25:24.000Z (over 4 years ago)
• Last Synced: 2024-11-08T15:11:49.803Z (3 months ago)
• Topics: artificial-intelligence, genetic-algorithm, neural-network, rickandmorty, simulation
• Language: Python
• Homepage: http://theokanning.com/backflip-simulation/
• Size: 1.08 MB
• Stars: 2
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Jerry Learns #

This simulation of Jerry Smith can be taught to walk or backflip using a NEAT genetic algorithm.

![asdf](backflip.gif)

## Simulation ##

Jerry Learns uses [Pymunk](http://www.pymunk.org/en/latest/) for its physics simulation and [Pygame](https://www.pygame.org)

 for graphics. Each joint is simulated as a pivot constraint, rotary limit, and a motor to provide motion. 

 

## Evolution ##

Jerry's brain is simulated with a simple neural network that takes his current body state and outputs the desired torque

for each of his joints. [NEAT-python](http://neat-python.readthedocs.io/en/latest/) generates a population of neural 

networks and evolves them over time.

## Creating New Behaviors ##

In order to create a behavior of your own, extend the Config class. This class is responsible for returning a fitness 

calculator, motion calculator, NEAT config, and starting joint angles.