A comparative investigation of non-linear activation functions in neural controllers for search-based game AI engineering

Tan, Tse Guan and Teo, Jason Tze Wi and Patricia Anthony (2011) A comparative investigation of non-linear activation functions in neural controllers for search-based game AI engineering. Artificial Intelligence Review. pp. 1-25. ISSN 0269-2821

[img]
Preview
Text
A_comparative_investigation_of_non.pdf

Download (44kB) | Preview

Abstract

The creation of intelligent video game controllers has recently become one of the greatest challenges in game artificial intelligence research, and it is arguably one of the fastest-growing areas in game design and development. The learning process, a very important feature of intelligent methods, is the result of an intelligent game controller to determine and control the game objects behaviors' or actions autonomously. Our approach is to use a more efficient learning model in the form of artificial neural networks for training the controllers. We propose a Hill-Climbing Neural Network (HillClimbNet) that controls the movement of the Ms. Pac-man agent to travel around the maze, gobble all of the pills and escape from the ghosts in the maze. HillClimbNet combines the hill-climbing strategy with a simple, feed-forward artificial neural network architecture. The aim of this study is to analyze the performance of various activation functions for the purpose of generating neural-based controllers to play a video game. Each non-linear activation function is applied identically for all the nodes in the network, namely log-sigmoid, logarithmic, hyperbolic tangent-sigmoid and Gaussian. In general, the results shows an optimum configuration is achieved by using log-sigmoid, while Gaussian is the worst activation function.

Item Type: Article
Keyword: Artificial neural networks, Computational intelligence in games, Gaussian, Hill-climbing, Hyperbolic tangent-sigmoid, Log-sigmoid, Logarithmic, Ms. Pac-Man
Subjects: Q Science > QA Mathematics > QA1-939 Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Department: SCHOOL > School of Engineering and Information Technology
Depositing User: ADMIN ADMIN
Date Deposited: 07 May 2012 16:34
Last Modified: 17 Oct 2017 12:05
URI: https://eprints.ums.edu.my/id/eprint/4081

Actions (login required)

View Item View Item