JamesGrisetti-Procedural Strategy Game Generation

JamesGrisetti-Procedural Strategy Game Generation - Towards...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Towards Procedural Strategy Game Generation: Evolving Complementary Unit Types Tobias Mahlmann, Julian Togelius, Georgios N. Yannakakis IT University of Copenhagen, Rued Langaards Vej 7, 2300 Copenhagen, Denmark { tmah, juto, yannakakis } @itu.dk Abstract. The Strategy Game Description Game Language (SGDL) is intended to become a complete description of all aspects of strategy games, including rules, parameters, scenarios, maps, and unit types. One of the main envisioned uses of SGDL, in combination with an evolution- ary algorithm and appropriate fitness functions, is to allow the genera- tion of complete new strategy games or variations of old ones. This paper presents a first version of SGDL, capable of describing unit types and their properties, together with plans for how it will be extended to other sub-domains of strategy games. As a proof of the viability of the idea and implementation, an experiment is presented where unit types are evolved so as to generate complementary properties. A fitness function based on Monte Carlo simulation of gameplay is devised to test complementarity. 1 Introduction Strategy games are one of the most enduring and consistently popular game genres, and have been around in one form or another for hundreds of years. This genre of games is famous for being one of the most cerebral; world championship tournaments exist for several such games. Meanwhile, the long learning curve and strong skill differentiation usually leads dedicated strategy game players to de- vote immense amounts of time to playing those games. Strategy games designed to mimic real life scenarios are commonly used for training and simulation. At the same time, the design, development and balancing of a modern digital strategy game such as the latest installments of the Civilization or Starcraft series is very labour-intensive and therefore expensive. Automating the design, development and tuning of strategy games would therefore be highly desirable. The field of procedural content generation (PCG) is devoted to algorithms that automatically create various types of game content. While isolated exam- ples of PCG in games date three decades back, and the SpeedTree software is commonly used for creating vegetation in commercial games, it is very rare to see PCG used for “necessary” content such as levels and mechanics rather than just for peripheral, “optional” content such as textures and collectable items in published games. Further, most PCG algorithms in published games are not controllable , simply generating random content within bounds. Recently, the term search-based procedural content generation (SBPCG) was proposed for PCG algorithms that build on global stochastic search algorithms 2 (such as evolutionary computation) and fitness functions designed to measure the quality of game content [14]. Examples of this approach include the evolution of platform game levels [7], of racing game tracks [11] and the distributed evolution of weapons in a space shooter game [3].of weapons in a space shooter game [3]....
View Full Document

This note was uploaded on 07/30/2011 for the course COP 4810 taught by Professor Staff during the Spring '11 term at University of Central Florida.

Page1 / 11

JamesGrisetti-Procedural Strategy Game Generation - Towards...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online