Automatic computer game balancing: a reinforcement learning approach

Authors:
Gustavo Andrade;Geber Ramalho;Hugo Santana;Vincent Corruble
Affiliations:
Universidade Federal de Pernambuco, CEP, Recife, Brazil;Universidade Federal de Pernambuco, CEP, Recife, Brazil;Universidade Federal de Pernambuco, CEP, Recife, Brazil;Université Paris, Paris
Venue:
Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
Year:
2005

Citing 2
Cited 9

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
A Theory of Fun for Game Design

A Theory of Fun for Game Design

A game AI production shell framework: generating AI opponents for geomorphic-isometric strategy games via modeling of expert player intuition

Proceedings of the 2nd international conference on Digital interactive media in entertainment and arts
Using genetically optimized artificial intelligence to improve gameplaying fun for strategical games

Sandbox '08 Proceedings of the 2008 ACM SIGGRAPH symposium on Video games
A combined tactical and strategic hierarchical learning framework in multi-agent games

Sandbox '08 Proceedings of the 2008 ACM SIGGRAPH symposium on Video games
Game engine design using data mining

AIA '08 Proceedings of the 26th IASTED International Conference on Artificial Intelligence and Applications
Using data mining for dynamic level design in games

ISMIS'08 Proceedings of the 17th international conference on Foundations of intelligent systems
PADS: enhancing gaming experience using profile-based adaptive difficulty system

Proceedings of the 5th ACM SIGGRAPH Symposium on Video Games
Time balancing with adaptive time-variant minigames

ICEC'11 Proceedings of the 10th international conference on Entertainment Computing
Towards player-driven procedural content generation

Proceedings of the 9th conference on Computing Frontiers
Gamification, Serious Games, Ludic Simulation, and other Contentious Categories

International Journal of Gaming and Computer-Mediated Simulations

Quantified Score

Hi-index	0.00

Visualization

Abstract

Designing agents whose behavior challenges human players adequately is a key issue in computer games development. This work presents a novel technique, based on reinforcement learning (RL), to automatically control the game level, adapting it to the human player skills in order to guarantee a good game balance. RL has commonly been used in competitive environments, in which the agent must perform as well as possible to beat its opponent. The innovative use of RL proposed here makes use of a challenge function, which estimates the current player's level, as well as changes on the action selection mechanism of the RL framework. The technique is applied to a fighting game, Knock'em, to provide empirical validation of the approach.