• Journal of Korea Game Society
• /
• v.19 no.3
• /
• pp.25-32
• /
• 2019

This paper proposes a automatic generation method of Match-3 game levels through genetic algorithm. It takes a lot of time and effort if persons have to control the level in the game. In this paper, the genetic algorithm is applied to create an appropriate block combination. We create block combination from integer DNA. Fitness is high if success probability played by computer is closer to given probability. Experiments have shown that computer-determined levels of difficulty have a significant impact on the results of game played persons.

• Journal of Korea Game Society
• /
• v.11 no.2
• /
• pp.19-28
• /
• 2011

Level design is one of the important factors in tower defense game development. The difficulty of tower defense game depends on its wave design. In general, it requires a lot of manual labor to generate well-balanced waves with fun. In this paper, we propose a new automated wave generation system by using a genetic algorithm. With our system, a game designer can easily generate an optimized wave by designating the difficulty level in the initial stage of game design. Our system can be useful in reducing the trial-errors in the initial level design process of tower defense game development.

• Journal of Internet Computing and Services
• /
• v.18 no.2
• /
• pp.43-51
• /
• 2017

As the game industry is blooming, the generation of contents is far behind the consumption of contents. With this reason, it is necessary to afford the game contents considering level of game player's skill. In order to effectively solve this problem, Procedural Content Generation(PCG) using Artificial Intelligence(AI) is one of the plausible options. This paper proposes the procedural method to generate various monsters considering level of player's skill using genetic algorithm. One gene consists of the properties of a monster and one genome consists of genes for various monsters. A generated monster is evaluated by battle simulation with a player and then goes through selection and crossover steps. Using our proposed scheme, players adaptive monsters are generated procedurally based on genetic algorithm and the variety of monsters which are generated with different number of genome is compared.