The multifaceted complexity of real-time strategy (RTS) games forces AI systems to break down policy computation into smaller subproblems – strategic planning, tactical planning, reactive control, and others. To further simplify planning at the strategic and tactical levels, state-of-the-art automatic techniques for this task, such as case-based planning, produce deterministic plans for what is...

Traditional artificial intelligence techniques do not perform well in applications such as real-time strategy games because of the extensive search spaces which need to be explored. In addition, this exploration must be carried out on-line during performance time; it cannot be precomputed. We have developed on-line casebased planning techniques that are effective in such domains. In this paper,...

Basically, in (one-player) war Real Time Strategy (wRTS) games a human player controls, in real time, an army consisting of a number of soldiers and her aim is to destroy the opponent’s assets where the opponent is a virtual (i.e., non-human player controlled) player that usually consists of a pre-programmed decision-making script. These scripts have usually associated some well-known problems ...

This short paper isolates a non-trivial class of games for which there exists a monotone relation between the size of pure strategy spaces and the number of pure Nash equilibria (Theorem). This class is that of two-player nice games, i.e., games with compact real intervals as strategy spaces and continuous and strictly quasi-concave payoff functions, assumptions met by many economic models. We ...

Real Time strategy games offer an environment where game AI is known to conduct actuality. One feature of realistic behavior in game AI is the ability to recognize the strategy of the opponent player. This is known as opponent modeling. In this paper, a classification Rough-Neuro hybrid model of the RTS opponent player behavior process is proposed. As a mean to achieve better game performance, ...

Learning how to defeat human players is a challenging task in today’s commercial computer games. This paper suggests a goal-directed hierarchical dynamic scripting approach for incorporating learning into real-time strategy games. Two alternatives for shortening the re-adaptation time when using dynamic scripting are also presented. Finally, this paper presents an effective way of throttling th...

We present a case-injected genetic algorithm player for Strike Ops, a real-time strategy game. Such strategy games are fundamentally resource allocation optimization problems and our previous work showed that genetic algorithms can play such games by solving the underlying resource allocation problem. This paper shows how we can learn to better respond to opponent actions (moves) by using case-...

The goal of my thesis work is to develop game analysis techniques capable of informing strategy design in large, complex games. Broadly defined, games are situations where multiple players make interacting decisions; each players’ choice depends on the choices of the other players. The formal study of games has origins in economics, but in recent years game theory has drawn increasing interest ...