Predicting army combat outcomes in StarCraft
Full Text:
PredictingArmyCombatOucomesInStarCraft-AIIDE2013.pdf 
Smart decision making at the tactical level is important
for Artificial Intelligence (AI) agents to perform well
in the domain of real-time strategy (RTS) games. This
paper presents a Bayesian model that can be used to predict
the outcomes of isolated battles, as well as predict
what units are needed to defeat a given army. Model parameters
are learned from simulated battles, in order to
minimize the dependency on player skill. We apply our
model to the game of StarCraft, with the end-goal of
using the predictor as a module for making high-level
combat decisions, and show that the model is capable
of making accurate predictions.
Citation
M. Stanescu,
S. Hernandez,
G. Erickson,
R. Greiner,
M. Buro.
"Predicting army combat outcomes in StarCraft". Artificial Intelligence and Interactive Entertainment Conference (AIIDE), pp 86-92, October 2013.
| Keywords: |
probabilistic graphical model, games, machine learning |
| Category: |
In Conference |
BibTeX
@incollection{Stanescu+al:AIIDE13,
author = {Marius Stanescu and Sergio Poo Hernandez and Graham Erickson and
Russ Greiner and Michael Buro},
title = {Predicting army combat outcomes in StarCraft},
Pages = {86-92},
booktitle = {Artificial Intelligence and Interactive Entertainment Conference
(AIIDE)},
year = 2013,
}Last Updated: February 12, 2020
Submitted by Sabina P 
