Neuromorphic Control for 3D Navigation in Minecraft Using Genetic Algorithms

TL;DR

This paper presents a neuromorphic control system using genetic algorithms to enable autonomous 3D navigation in Minecraft, focusing on parkour-style traversal by optimizing neural network weights.

Contribution

It introduces a genetic algorithm approach to train neural networks for efficient 3D navigation in Minecraft's complex environment.

Findings

Successfully generated neural network weights for navigation tasks

Achieved efficient traversal of challenging parkour obstacles

Demonstrated autonomous decision-making in a dynamic voxel environment

Abstract

The popular 2009 voxel based videogame, Minecraft, contains several distinct disciplines. One of which is "parkour," gameplay that focuses on traversing a world's environment with maximum efficiency. The Minecraft online community has turned the game's physics engine into dynamic puzzles, requiring players to masterfully manipulate motion mechanics through frame precise timing of keystrokes. Actions such as sprinting, sneaking, and mouse direction are all combined to clear specific difficult jumps. Through this project, we design a genetic algorithm to generate weights for a neural network to autonomously evaluate inputs for block distances, terrain, and obstacles to determine the most optimal pathing.