An investigation of two real time machine learning techniques that could enhance the adaptability of game AI agents


Autoria(s): King, David J.; Bennett, Cassie
Contribuinte(s)

Abertay University. School of Arts Media & Computer Games

Data(s)

08/12/2016

08/12/2016

2016

Resumo

Developers strive to create innovative Artificial Intelligence (AI) behaviour in their games as a key selling point. Machine Learning is an area of AI that looks at how applications and agents can be programmed to learn their own behaviour without the need to manually design and implement each aspect of it. Machine learning methods have been utilised infrequently within games and are usually trained to learn offline before the game is released to the players. In order to investigate new ways AI could be applied innovatively to games it is wise to explore how machine learning methods could be utilised in real-time as the game is played, so as to allow AI agents to learn directly from the player or their environment. Two machine learning methods were implemented into a simple 2D Fighter test game to allow the agents to fully showcase their learned behaviour as the game is played. The methods chosen were: Q-Learning and an NGram based system. It was found that N-Grams and QLearning could significantly benefit game developers as they facilitate fast, realistic learning at run-time.

Identificador

King, D. and Bennett, C. 2016. An investigation of two real time machine learning techniques that could enhance the adaptability of game AI agents. GameOn’2016 17th International Conference on Intelligent Games and Simulation, Lisbon, Portugal, 13-15 September.

978-90-77381-946

http://hdl.handle.net/10373/2553

Idioma(s)

en

Publicador

EUROSIS

Relação

GameOn'2016 Proceedings

Direitos

The published paper © EUROSIS is published in the Proceedings of the 17th International Conference on Intelligent Games and Simulation available from www.eurosis.org

Palavras-Chave #Artificial intelligence (AI) #Adaptive game AI #Q-learning #N-gram prediction
Tipo

Conference Paper

published

non peer-reviewed

accepted