Evolving player-specific content for level based arcade games

Authors:
Sanjeev Satheesh;Harikrishna Narasimhan;Pramala Senthil
Affiliations:
Anna University, Tamil Nadu, India;Anna University, Tamil Nadu, India;Thiagarajar College of Engineering, Tamil Nadu, India
Venue:
Proceedings of the 4th International Conference on Foundations of Digital Games
Year:
2009

Citing 2
Cited 0

What makes things fun to learn? heuristics for designing instructional computer games

SIGSMALL '80 Proceedings of the 3rd ACM SIGSMALL symposium and the first SIGPC symposium on Small systems
A Theory of Fun for Game Design

A Theory of Fun for Game Design

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this poster, we attempt to generate content for single player level based arcade games, according to the player's skill. The objective is to make the game just enough challenging for the player. An evolvable representation of the game content is developed. The player's performance is measured after completion of each level. An Artificial Neural Network (ANN) is used to estimate the expected performance for the level content. The deviation of the actual performance of the player from the expected performance is used to estimate the toughness of the next level. A Genetic Algorithm then evolves the next level. The fittest candidate is the one matching the required toughness.