Generating Levels That Teach Mechanics
arXiv:1807.06734 · doi:10.1145/3235765.3235820
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.
arXiv comment8 pages, 7 figures, PCG Workshop at FDG 2018, 9th International Workshop on Procedural Content Generation (PCG2018)
References in corpus (6)
- The VGLC: The Video Game Level Corpus
- AtDelfi: Automatically Designing Legible, Full Instructions For Games
- Talakat: Bullet Hell Generation through Constrained Map-Elites
- "Press Space to Fire": Automatic Video Game Tutorial Generation
- Automatic Mapping of NES Games with Mappy
- Deriving Quests from Open World Mechanics