"Press Space to Fire": Automatic Video Game Tutorial Generation
This addresses the need for efficient tutorial creation in game development, but it is incremental as it builds on existing AI and game frameworks without introducing a new core method.
The paper tackles the problem of automatically generating video game tutorials by framing it as an AI challenge, proposing approaches like natural language descriptions, instructive levels, and agent demonstrations, and suggests using the General Video Game AI framework as a testbed.
We propose the problem of tutorial generation for games, i.e. to generate tutorials which can teach players to play games, as an AI problem. This problem can be approached in several ways, including generating natural language descriptions of game rules, generating instructive game levels, and generating demonstrations of how to play a game using agents that play in a human-like manner. We further argue that the General Video Game AI framework provides a useful testbed for addressing this problem.