Generating Levels That Teach Mechanics
This addresses the challenge of creating gameplay experiences that teach mechanics for game developers, but it is incremental as it builds on existing level generation and agent-based testing methods.
The paper tackles the problem of automatically generating game tutorials by evolving small levels in the Mario AI Framework that require specific actions to complete, using variations of a perfect A* agent to test failure conditions.
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.