|
Artificial Intelligence for Spelunky Computer Game
Závorka, Kamil ; Gemrot, Jakub (advisor) ; Ježek, Pavel (referee)
Spelunky is one of the desktop games, where player control agent in labyrinth and his task is to reach the exit. In this labyrinth there are many threats and quests, which makes the game interesting for making artificial intelligence, that can be adjusted for these threats and quests. The goal of this work was to create a framework for comfortable programming of artificial intelligence for this game. Although there is a tool named SpelunkBotAPI for its writing and executing, the API of this tool provides only basic controlling of agent and it is hard to use it. The approach, that I chose for this work, used the existing API and built a framework above it, that will be easier to use. For more intuitive using of the framework, this work crates GOAP (Goal Oriented Action Planner), that uses its functionality for reaching goals specified by the programmer.
|