StarCraft Bots and Competitions

Definition Real-Time Strategy (RTS) games is a sub-genre of strategy games where players need to build an economy (gathering resources and building a base) and military power (training units and researching technologies) in order to defeat their opponents (destroying their army and base). Artificial Intelligence (AI) problems related to RTS games deal with the behavior of an artificial player. Since 2010, many international competitions have been organized to match AIs, or bots, playing to the RTS game StarCraft. This chapter presents a review of all major international competitions from 2010 until 2015, and details some competing StarCraft bots. State of the Art Bots for StarCraft Thanks to the recent organization of international game AI competitions fo-cused around the popular StarCraft game, several groups have been working on integrating many of the techniques developed for RTS game AI into complete "bots", capable of playing complete StarCraft games. In this chapter we will overview some of the currently available top bots, and their results of recent competitions.

[1]  Santiago Ontañón,et al.  Kiting in RTS Games Using Influence Maps , 2012, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

[2]  Gabriel Synnaeve,et al.  A Bayesian model for RTS units control applied to StarCraft , 2011, 2011 IEEE Conference on Computational Intelligence and Games (CIG'11).

[3]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[4]  Björn Persson Mattsson,et al.  Automatic Observer Script for StarCraft: Brood War Bot Games (technical report) , 2015, ArXiv.

[5]  Bhaskara Marthi,et al.  Concurrent Hierarchical Reinforcement Learning , 2005, IJCAI.

[6]  Tom Chothia,et al.  SCAIL: An integrated Starcraft AI system , 2012, 2012 IEEE Conference on Computational Intelligence and Games (CIG).

[7]  Santiago Ontañón,et al.  ON‐LINE CASE‐BASED PLANNING , 2010, Comput. Intell..

[8]  Johan Hagelbäck,et al.  Potential-field based navigation in StarCraft , 2012, 2012 IEEE Conference on Computational Intelligence and Games (CIG).

[9]  David W. Aha,et al.  Learning to Win: Case-Based Plan Selection in a Real-Time Strategy Game , 2005, Künstliche Intell..

[10]  Michael Buro,et al.  Build Order Optimization in StarCraft , 2011, AIIDE.

[11]  Nick Hawes,et al.  Evolutionary Learning of Goal Priorities in a Real-Time Strategy Game , 2012, AIIDE.