Řízení boje ve hře Starcraft II pomocí umělé inteligence

Abstract

Táto práca sa zaoberá využitím umelej inteligencie a návrh funkčného modulu pre strategickú hru StarCraft II. Riešenie využíva neurónové siete a Q-learning pre boj. Pre implementáciu systému a jej prepojenie s hrou StarCraft používam StarCraft 2 Learning Environment. Vyhodnotenie systému je založené na jej schopnosti vykonať pokrok.This thesis focuses on the use of Artificial Intelligence and design of working module in Real-Time Strategy (RTS) game, StarCraft II. The proposed solution uses Neural Network and Q-learning for combat management. For implementation, the StarCraft 2 Learning Environment has been used as a means of communication between the designed system and the game. Evaluation of the system is based on its ability to make progress over time.