A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence
Recently, the growth of Artificial Intelligence (AI) has provided a set of effective techniques for designing computer-based controllers to perform various tasks autonomously in game area, specifically to produce intelligent optimal game controllers for playing video and computer games. This paper...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2013
|
| Online Access: | http://journalarticle.ukm.my/6646/1/4297-9967-1-PB.pdf |
| _version_ | 1796930347524423680 |
|---|---|
| author | Tse, Guan Tan Jason, Teo Kim, On Chin Alfred, Rayner |
| author_facet | Tse, Guan Tan Jason, Teo Kim, On Chin Alfred, Rayner |
| author_sort | Tse, Guan Tan |
| collection | UKM |
| description | Recently, the growth of Artificial Intelligence (AI) has provided a set of effective techniques for designing
computer-based controllers to perform various tasks autonomously in game area, specifically to produce
intelligent optimal game controllers for playing video and computer games. This paper explores the use of the
competitive fitness strategy: K Random Opponents (KRO) in a multiobjective approach for evolving Artificial
Neural Networks (ANNs) that act as controllers for the Ms. Pac-man agent. The Pareto Archived Evolution
Strategy (PAES) algorithm is used to generate a Pareto optimal set of ANNs that optimize the conflicting
objectives of maximizing game scores and minimizing neural network complexity. Furthermore, an improved
version, namely PAESNet_KRO, is proposed, which incorporates in contrast to its predecessor KRO strategy.
The results are compared with PAESNet. From the discussions, it is found that PAESNet_KRO provides better
solutions than PAESNet. The PAESNet_KRO can evolve a set of nondominated solutions that cover the solutions
of PAESNet. |
| first_indexed | 2024-03-06T04:01:43Z |
| format | Article |
| id | ukm.eprints-6646 |
| institution | Universiti Kebangsaan Malaysia |
| language | English |
| last_indexed | 2024-03-06T04:01:43Z |
| publishDate | 2013 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| record_format | dspace |
| spelling | ukm.eprints-66462016-12-14T06:41:48Z http://journalarticle.ukm.my/6646/ A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence Tse, Guan Tan Jason, Teo Kim, On Chin Alfred, Rayner Recently, the growth of Artificial Intelligence (AI) has provided a set of effective techniques for designing computer-based controllers to perform various tasks autonomously in game area, specifically to produce intelligent optimal game controllers for playing video and computer games. This paper explores the use of the competitive fitness strategy: K Random Opponents (KRO) in a multiobjective approach for evolving Artificial Neural Networks (ANNs) that act as controllers for the Ms. Pac-man agent. The Pareto Archived Evolution Strategy (PAES) algorithm is used to generate a Pareto optimal set of ANNs that optimize the conflicting objectives of maximizing game scores and minimizing neural network complexity. Furthermore, an improved version, namely PAESNet_KRO, is proposed, which incorporates in contrast to its predecessor KRO strategy. The results are compared with PAESNet. From the discussions, it is found that PAESNet_KRO provides better solutions than PAESNet. The PAESNet_KRO can evolve a set of nondominated solutions that cover the solutions of PAESNet. Penerbit Universiti Kebangsaan Malaysia 2013-12 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/6646/1/4297-9967-1-PB.pdf Tse, Guan Tan and Jason, Teo and Kim, On Chin and Alfred, Rayner (2013) A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence. Asia-Pacific Journal of Information Technology and Multimedia, 2 (2). pp. 53-61. ISSN 2289-2192 http://ejournals.ukm.my/apjitm/index |
| spellingShingle | Tse, Guan Tan Jason, Teo Kim, On Chin Alfred, Rayner A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence |
| title | A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence |
| title_full | A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence |
| title_fullStr | A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence |
| title_full_unstemmed | A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence |
| title_short | A coevolutionary multiobjective evolutionary algorithm for game artificial intelligence |
| title_sort | coevolutionary multiobjective evolutionary algorithm for game artificial intelligence |
| url | http://journalarticle.ukm.my/6646/1/4297-9967-1-PB.pdf |
| work_keys_str_mv | AT tseguantan acoevolutionarymultiobjectiveevolutionaryalgorithmforgameartificialintelligence AT jasonteo acoevolutionarymultiobjectiveevolutionaryalgorithmforgameartificialintelligence AT kimonchin acoevolutionarymultiobjectiveevolutionaryalgorithmforgameartificialintelligence AT alfredrayner acoevolutionarymultiobjectiveevolutionaryalgorithmforgameartificialintelligence AT tseguantan coevolutionarymultiobjectiveevolutionaryalgorithmforgameartificialintelligence AT jasonteo coevolutionarymultiobjectiveevolutionaryalgorithmforgameartificialintelligence AT kimonchin coevolutionarymultiobjectiveevolutionaryalgorithmforgameartificialintelligence AT alfredrayner coevolutionarymultiobjectiveevolutionaryalgorithmforgameartificialintelligence |