Generating Levels That Teach Mechanics

TL;DR

This paper presents a method for automatically generating small game levels that teach players specific mechanics by requiring agents with limited capabilities to succeed, thereby enhancing gameplay learning.

Contribution

It introduces a novel approach to generate levels that specifically teach game mechanics by leveraging variations of a perfect A* agent with limited abilities.

Findings

Generated levels effectively teach specific mechanics.

Limited-capability agents fail on levels that require unlearned actions.

Levels can be used to improve player understanding of game mechanics.

Abstract

The automatic generation of game tutorials is a challenging AI problem. While it is possible to generate annotations and instructions that explain to the player how the game is played, this paper focuses on generating a gameplay experience that introduces the player to a game mechanic. It evolves small levels for the Mario AI Framework that can only be beaten by an agent that knows how to perform specific actions in the game. It uses variations of a perfect A* agent that are limited in various ways, such as not being able to jump high or see enemies, to test how failing to do certain actions can stop the player from beating the level.