Adaptive and Natural Computing Algorithms

Colm O'Riordan

Adaptive and Natural Computing Algorithms

Colm O'Riordan

Computer Science

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

This paper presents a new approach to the evolution of blackjack strategies, that of cultural learning. Populations of neural network agents are evolved using a genetic algorithm and at each generation the best performing agents are selected as teachers. Cultural learning is implemented through a hidden layer in each teachers neural network that is used to produce utterances which are imitated by its pupils during many games of blackjack. Results show that the cultural learning approach outperforrns previous work and equals the best known non-card counting human approaches.

Original language	English (Ireland)
Title of host publication	Evolving blackjack strategies using cultural learning
Number of pages	4
Publication status	Published - 1 May 2005

Authors (Note for portal: view the doc link for the full list of authors)

Authors
Curran, D,O'Riordan, C,Ribeiro, B,Albrecht, RF,Dobnikar, A,Pearson, DW,Steele, NC

Cite this

@inproceedings{1d210d59b5ca47ce9b03e88832fd7572,

title = "Adaptive and Natural Computing Algorithms",

abstract = "This paper presents a new approach to the evolution of blackjack strategies, that of cultural learning. Populations of neural network agents are evolved using a genetic algorithm and at each generation the best performing agents are selected as teachers. Cultural learning is implemented through a hidden layer in each teachers neural network that is used to produce utterances which are imitated by its pupils during many games of blackjack. Results show that the cultural learning approach outperforrns previous work and equals the best known non-card counting human approaches.",

author = "Colm O'Riordan",

year = "2005",

month = may,

day = "1",

language = "English (Ireland)",

booktitle = "Evolving blackjack strategies using cultural learning",

}

TY - GEN

T1 - Adaptive and Natural Computing Algorithms

AU - O'Riordan, Colm

PY - 2005/5/1

Y1 - 2005/5/1

N2 - This paper presents a new approach to the evolution of blackjack strategies, that of cultural learning. Populations of neural network agents are evolved using a genetic algorithm and at each generation the best performing agents are selected as teachers. Cultural learning is implemented through a hidden layer in each teachers neural network that is used to produce utterances which are imitated by its pupils during many games of blackjack. Results show that the cultural learning approach outperforrns previous work and equals the best known non-card counting human approaches.

AB - This paper presents a new approach to the evolution of blackjack strategies, that of cultural learning. Populations of neural network agents are evolved using a genetic algorithm and at each generation the best performing agents are selected as teachers. Cultural learning is implemented through a hidden layer in each teachers neural network that is used to produce utterances which are imitated by its pupils during many games of blackjack. Results show that the cultural learning approach outperforrns previous work and equals the best known non-card counting human approaches.

M3 - Conference Publication

BT - Evolving blackjack strategies using cultural learning

ER -

Adaptive and Natural Computing Algorithms

Abstract

Authors (Note for portal: view the doc link for the full list of authors)

Fingerprint

Cite this