Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game

In this paper, we present a study of evolving artificial neural network controllers for autonomously playing maze-based video game. A system using multi-objective evolutionary algorithm is developed, which is called as Pareto Archived Evolution Strategy Neural Network(PAESNet), with the attempt to f...

Full description

Bibliographic Details
Main Authors:	Tse, Guan Tan, Jason Teo, Kim, On Chin, Patricia Anthony
Format:	Article
Language:	English
Published:	Trans Tech Publications, Switzerland 2013
Subjects:	TA Engineering (General). Civil engineering (General)
Online Access:	http://eprints.ums.edu.my/20488/ http://eprints.ums.edu.my/20488/1/Pareto%20Ensembles%20for%20evolutionary%20Synthesis%20of%20Neurocontrollers%20in%20a%202D%20Maze.pdf

id	ums-20488
recordtype	eprints
spelling	ums-204882018-07-17T05:54:43Z http://eprints.ums.edu.my/20488/ Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game Tse, Guan Tan Jason Teo, Kim, On Chin Patricia Anthony, TA Engineering (General). Civil engineering (General) In this paper, we present a study of evolving artificial neural network controllers for autonomously playing maze-based video game. A system using multi-objective evolutionary algorithm is developed, which is called as Pareto Archived Evolution Strategy Neural Network(PAESNet), with the attempt to find a set of Pareto optimal solutions by simultaneously optimizing two conflicting objectives. The experiments are designed to address two research aims investigating: (1) evolving weights (including biases) of the connections between the neurons and structure of the network through multi-objective evolutionary algorithm in order to reduce its runtime operation and complexity, (2) improving the generalization ability of the networks by using neural network ensemble model. A comparative analysis between the single network model as the baseline system and the model built based on the neural ensemble are presented. The evidence from this study suggests that Pareto multi-objective paradigm and neural network ensembles can be effective for creating and controlling the behaviors of video game characters. Trans Tech Publications, Switzerland 2013 Article PeerReviewed text en http://eprints.ums.edu.my/20488/1/Pareto%20Ensembles%20for%20evolutionary%20Synthesis%20of%20Neurocontrollers%20in%20a%202D%20Maze.pdf Tse, Guan Tan and Jason Teo, and Kim, On Chin and Patricia Anthony, (2013) Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game. Applied Mechanics and Materials. pp. 3173-3177. ISSN 1662-7482
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Sabah Malaysia
building	UMS Institutional Repository
collection	Online Access
language	English
topic	TA Engineering (General). Civil engineering (General)
spellingShingle	TA Engineering (General). Civil engineering (General) Tse, Guan Tan Jason Teo, Kim, On Chin Patricia Anthony, Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game
description	In this paper, we present a study of evolving artificial neural network controllers for autonomously playing maze-based video game. A system using multi-objective evolutionary algorithm is developed, which is called as Pareto Archived Evolution Strategy Neural Network(PAESNet), with the attempt to find a set of Pareto optimal solutions by simultaneously optimizing two conflicting objectives. The experiments are designed to address two research aims investigating: (1) evolving weights (including biases) of the connections between the neurons and structure of the network through multi-objective evolutionary algorithm in order to reduce its runtime operation and complexity, (2) improving the generalization ability of the networks by using neural network ensemble model. A comparative analysis between the single network model as the baseline system and the model built based on the neural ensemble are presented. The evidence from this study suggests that Pareto multi-objective paradigm and neural network ensembles can be effective for creating and controlling the behaviors of video game characters.
format	Article
author	Tse, Guan Tan Jason Teo, Kim, On Chin Patricia Anthony,
author_facet	Tse, Guan Tan Jason Teo, Kim, On Chin Patricia Anthony,
author_sort	Tse, Guan Tan
title	Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game
title_short	Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game
title_full	Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game
title_fullStr	Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game
title_full_unstemmed	Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game
title_sort	pareto ensembles for evolutionary synthesis of neurocontrollers in a 2d maze-based video game
publisher	Trans Tech Publications, Switzerland
publishDate	2013
url	http://eprints.ums.edu.my/20488/ http://eprints.ums.edu.my/20488/1/Pareto%20Ensembles%20for%20evolutionary%20Synthesis%20of%20Neurocontrollers%20in%20a%202D%20Maze.pdf
first_indexed	2018-09-05T09:43:58Z
last_indexed	2018-09-05T09:43:58Z
_version_	1610760206589886464

Pareto Ensembles for evolutionary Synthesis of Neurocontrollers in a 2D Maze-based video game

Similar Items