Search, Abstractions and Learning in Real-Time Strategy Games A Dissertation Summary

Barriga, Nicolas A.

Abstract

Real-Time Strategy Games' large state and action spaces pose a significant hurdle to traditional AI techniques. We propose decomposing the game into sub-problems and integrating the partial solutions into action scripts that can be used as abstract actions by a search or machine learning algorithm. The resulting high level algorithm produces sound strategic choices, and can then be combined with a low-level search algorithm to refine tactical choices. We show strong results in SparCraft, Starcraft: Brood War and mu\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mu $$\end{document}RTS against state-of-the-art agents. We expect advances in RTS AI can be used in commercial videogames for playtesting and game balancing, while also having possible real-world applications.

Más información

Título según WOS: Search, Abstractions and Learning in Real-Time Strategy Games A Dissertation Summary
Título de la Revista: KUNSTLICHE INTELLIGENZ
Volumen: 34
Número: 1
Editorial: SPRINGER HEIDELBERG
Fecha de publicación: 2020
Página de inicio: 101
Página final: 103
DOI:

10.1007/S13218-019-00614-0

Notas: ISI