Learning Competitive Minecraft Minigames with Reinforcement Learning
Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Tartu Ülikool
Abstract
In recent years, deep reinforcement learning methods have successfully been used to
play complex games like Go, StarCraft II, and Dota 2 at a professional level. In this
thesis, reinforcement learning methods are used to train artificial agents in the game of
Minecraft. Various competitive 1v1 Minecraft minigames from one of the most popular
Minecraft servers Hypixel are selected. Deep neural networks are trained to play each
of these games using proximal policy optimization algorithms and self-play. In all the
games, artificial agents were able to play the game at least on a beginner level. In one
game, the agent reached the level of expert human players.
Description
Keywords
reinforcement learning, artificial neural networks, self-play