An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four

In this paper, we investigate an integration of individual and social learning, utilising co-evolutionary neural networks. Individual learning takes place by playing copies of a player against itself. Social learning allows poor performing players to learn from those players, which are playing at a...

Full description

Bibliographic Details
Main Authors: Yaakob, Razali, Mahdin, Hairulnizam
Format: Conference or Workshop Item
Language:English
Published: 2007
Online Access:http://psasir.upm.edu.my/id/eprint/60121/1/RazaliUTHM.pdf
_version_ 1796977238770450432
author Yaakob, Razali
Mahdin, Hairulnizam
author_facet Yaakob, Razali
Mahdin, Hairulnizam
author_sort Yaakob, Razali
collection UPM
description In this paper, we investigate an integration of individual and social learning, utilising co-evolutionary neural networks. Individual learning takes place by playing copies of a player against itself. Social learning allows poor performing players to learn from those players, which are playing at a higher level. The networks are evolved via evolutionary strategies with the network output being used as input to a minimax search tree. Our experiments show that learning is taking place at the 99% confidence level. In terms of performance, the co-evolutionary neural network player has the ability to block two adjacent stones of an opponent.
first_indexed 2024-03-06T09:37:15Z
format Conference or Workshop Item
id upm.eprints-60121
institution Universiti Putra Malaysia
language English
last_indexed 2024-03-06T09:37:15Z
publishDate 2007
record_format dspace
spelling upm.eprints-601212018-04-12T04:37:15Z http://psasir.upm.edu.my/id/eprint/60121/ An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four Yaakob, Razali Mahdin, Hairulnizam In this paper, we investigate an integration of individual and social learning, utilising co-evolutionary neural networks. Individual learning takes place by playing copies of a player against itself. Social learning allows poor performing players to learn from those players, which are playing at a higher level. The networks are evolved via evolutionary strategies with the network output being used as input to a minimax search tree. Our experiments show that learning is taking place at the 99% confidence level. In terms of performance, the co-evolutionary neural network player has the ability to block two adjacent stones of an opponent. 2007 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/60121/1/RazaliUTHM.pdf Yaakob, Razali and Mahdin, Hairulnizam (2007) An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four. In: 1st Regional Conference on Computational Science and Technologies (RCCST 2007), 29-30 Nov. 2007, Shangri-la Tanjung Aru Resort and Spa, Kota Kinabalu, Sabah. (pp. 97-101).
spellingShingle Yaakob, Razali
Mahdin, Hairulnizam
An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four
title An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four
title_full An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four
title_fullStr An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four
title_full_unstemmed An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four
title_short An integration of individual and social learning in a co-evolutionary approach to the game of Connect-Four
title_sort integration of individual and social learning in a co evolutionary approach to the game of connect four
url http://psasir.upm.edu.my/id/eprint/60121/1/RazaliUTHM.pdf
work_keys_str_mv AT yaakobrazali anintegrationofindividualandsociallearninginacoevolutionaryapproachtothegameofconnectfour
AT mahdinhairulnizam anintegrationofindividualandsociallearninginacoevolutionaryapproachtothegameofconnectfour
AT yaakobrazali integrationofindividualandsociallearninginacoevolutionaryapproachtothegameofconnectfour
AT mahdinhairulnizam integrationofindividualandsociallearninginacoevolutionaryapproachtothegameofconnectfour