TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games

11/01/2016
by   Gabriel Synnaeve, et al.
0

We present TorchCraft, a library that enables deep learning research on Real-Time Strategy (RTS) games such as StarCraft: Brood War, by making it easier to control these games from a machine learning framework, here Torch. This white paper argues for using RTS games as a benchmark for AI research, and describes the design and components of TorchCraft.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/09/2012

Experiments with Game Tree Search in Real-Time Strategy Games

Game tree search algorithms such as minimax have been used with enormous...
research
11/19/2012

A Dataset for StarCraft AI & an Example of Armies Clustering

This paper advocates the exploration of the full state of recorded real-...
research
02/21/2020

Real-Time Visualization in Non-Isotropic Geometries

Non-isotropic geometries are of interest to low-dimensional topologists,...
research
08/10/2020

Cross-Platform Games in Kotlin

This demo paper describes a simple and practical approach to writing cro...
research
01/07/2021

Who's a Good Boy? Reinforcing Canine Behavior in Real-Time using Machine Learning

In this paper we outline the development methodology for an automatic do...
research
09/25/2020

Design and Implementation of TAG: A Tabletop Games Framework

This document describes the design and implementation of the Tabletop Ga...
research
05/18/2022

Terrain Analysis in StarCraft 1 and 2 as Combinatorial Optimization

Terrain analysis in Real-Time Strategy games is a necessary step to allo...

Please sign up or login with your details

Forgot password? Click here to reset