A comparison of two sigmoidal-type activation functions in video game controller evolution

Tan, Tse Guan and Teo, Jason Tze Wi and Patricia Anthony, (2011) A comparison of two sigmoidal-type activation functions in video game controller evolution. In: 2011 IEEE Conference on Sustainable Utilization Development in Engineering and Technology, STUDENT 2011;Semenyih;20 October 2011through21 October 2011, 20-21 October 2011, Semenyih, Kuala Lumpur, Malaysia.

Full text not available from this repository.


This paper presents an empirical comparison of two sigmoidal-type activation functions in evolutionary artificial neural network models. They are the log-sigmoid and hyperbolic tangent sigmoid activation functions which were investigated in order for evolving neural network controllers to play a classic video game. A Hill-Climbing Neural Network (HillClimbNet) was developed using the hill-climbing method together with a feedforward neural network to automatically create an intelligent controller that can play the screen-capture of Ms. Pac-man arcade game. The experimental results showed that that the HillClimbNet with log-sigmoid outperforms the HillClimbNet with hyperbolic tangent sigmoid when used in the hidden and output layers of the network when the agent plays the game.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: Feed-forward artificial neural network, Hill-climbing, Hyperbolic tangent sigmoid, Log-sigmoid, ms. pac-man
Subjects: ?? TK7800-8360 ??
Q Science > QA Mathematics > QA76 Computer software
Depositing User: Unnamed user with email storage.bpmlib@ums.edu.my
Date Deposited: 30 Apr 2012 08:32
Last Modified: 08 Sep 2014 08:13
URI: http://eprints.ums.edu.my/id/eprint/4052

Actions (login required)

View Item View Item

Browse Repository
   UMS News
Quick Search

   Latest Repository

Link to other Malaysia University Institutional Repository

Malaysia University Institutional Repository