Standard Economic Models in Nonstandard Settings – StarCraft: Brood War

  title={Standard Economic Models in Nonstandard Settings – StarCraft: Brood War},
  author={Bryan S. Weber},
  journal={2018 IEEE Conference on Computational Intelligence and Games (CIG)},
  • Bryan S. Weber
  • Published 1 August 2018
  • Economics
  • 2018 IEEE Conference on Computational Intelligence and Games (CIG)
This paper reviews an entrant to this year’s Star-Craft: Brood War AI tournament, CUNYbot. [] Key Method CUNYbot first tunes the economic model parameters between games using a genetic algorithm, allowing it to learn an optimal static k for each built-in AI race. In the second step of the project, CUNYbot models the opponent during the game and is permitted to react to the opponent’s inferred choices in k. The reactive model adopts a greedy "tit-for-tat" style strategy against all three races. This paper…

Figures and Tables from this paper

Resolving Simultaneity Bias: Using Features to Estimate Causal Effects in Competitive Games
In this paper, we walk through an application of the instrumental variables (IV) and control function approach (CF) estimators to identify the causal effect of in-game features on the probability of


Learning to Win: Case-Based Plan Selection in a Real-Time Strategy Game
A plan retrieval algorithm is introduced that, by using three key sources of domain knowledge, removes the assumption of a static opponent and significantly outperforms the best among a set of genetically evolved plans when tested against random Wargus opponents.
The Diablo 3 Economy: An Agent Based Approach
Designers of MMOs such as Diablo 3 face economic problems much like policy makers in the real world, e.g. inflation and distributional issues. Solving economic problems through regular updates
Towards automatic StarCraft strategy generation using genetic programming
The preliminary results of StarCraftGP are presented, a framework able to evolve a complete strategy for StarCraft, from the building plan, to the composition of squads, up to the set of rules that define the bot's behavior during the game.
World of Warcraft: The Viability of Massively Multiplayer Online Role-Playing Games as Platforms for Modeling and Evaluating Perfect Competition
The objective of the study was to determine whether the virtual economy of World of Warcraft in fact behaves like a real world economy, whether it is a competitive free market approaching the ideal
Prediction of early stage opponents strategy for StarCraft AI using scouting and machine learning
Experimental results show that the machine learning approach based on realistic scouting data can be beneficial in predicting the opponents early-stage strategy.
Understanding "Gold Farming" and Real-Money Trading as the Intersection of Real and Virtual Economies
This paper has three purposes. First, it extends the range of economic ideas that have been applied to massively-multiplayer online games (MMOGs), drawing on scale economies, exchange rates, and
Special tactics: A Bayesian approach to tactical decision-making
A generative Bayesian model of tactical attacks in strategy games, which can be used both to predict attacks and to take tactical decisions, and which claims that learning, being it supervised or through reinforcement, adapts to skewed data sources.
Continual online evolutionary planning for in-game build order adaptation in StarCraft
COEP was added to an open source StarCraft bot called UAlbertaBot and is able to outperform the built-in bots in the game as well as being competitive against a number of scripted opening strategies.
A Multi-objective Genetic Algorithm for Build Order Optimization in StarCraft II
This article presents a modified version of the multi-objective genetic algorithm NSGA II in order to find optimal opening strategies in the real-time strategy game StarCraft II. Based on an
Axelrod's The Evolution of Cooperation
* Most economists who have studied the behavior of firms have at one time or another wrestled with such questions as: How is collusion among firms sustained? Why do firms sometimes maintain product