OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Flappylearning

Flappylearning is an open-source JavaScript demonstration that evolves neural-network controllers to play Flappy Bird. Its NeuroEvolution.js interface generates candidate networks, accepts scores after evaluation, and uses configured selection and mutation settings to produce later generations.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Flappylearning — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a compact, game-specific example of a JavaScript neuroevolution loop, or a starting point for experimenting with scored neural-network populations.

Who it is for

  • Developers exploring neuroevolution in JavaScript
  • Learners studying how neural-network selection and mutation can be demonstrated in a simple game

Documented uses

  • Generate candidate neural networks for a game-playing population
  • Score evaluated networks and produce successive generations
  • Inspect how settings such as elitism, random behaviour and mutation affect the evolutionary process
Before you choose

Requirements & limits

The public GitHub repository is open source and reports an MIT license.

  • The documented game integration is Flappy Bird, so other tasks require adapting the example.
  • Population size, network structure, elitism, random behaviour and mutation settings are configurable.
  • The interface expects the integrating game or program to evaluate networks and submit scores.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Use NeuroEvolution.js to produce scored generations

Follow the documented interface for initializing a population, generating candidate networks, and submitting their evaluation scores.

Before you start

  • JavaScript project using NeuroEvolution.js
  • A way to evaluate each generated network and assign it a score

Steps

  1. Initialize NeuroEvolution.js with network and population options.

  2. Call nextGeneration() to obtain candidate networks.

  3. Evaluate a network and call networkScore with that network and its score when evaluation ends.

  4. Call nextGeneration() to generate the following population.

Expected outcome

A generation cycle in which evaluated networks receive scores and the configured evolutionary process produces a subsequent generation.

Guide limitations

  • The README documents the library interface and identifies Game.js as the Flappy Bird integration; it does not provide a complete setup or execution procedure.
  • Results depend on the evaluation and scoring logic supplied by the integrating game.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
xviniette/FlappyLearning · Official homepage title · retained in its source language
How we review sourcesSuggest a correction