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

David J. King, Cassie Bennett

Research output: Chapter in Book/Report/Conference proceedingConference contribution

169 Downloads (Pure)

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of GAMEON'2016
Subtitle of host publicationthe 17th International Conference on Intelligent Games and Simulation
EditorsHelena Barabas
PublisherEUROSIS
Pages41-48
Number of pages9
ISBN (Print)9789077381946
Publication statusPublished - 30 Sep 2016
EventGAMEON'2016: 17th International Conference on Intelligent Games and Simulation - Universidade Nova de Lisboa, Lisbon , Portugal
Duration: 13 Sep 201615 Sep 2016

Conference

ConferenceGAMEON'2016
CountryPortugal
CityLisbon
Period13/09/1615/09/16

Fingerprint Dive into the research topics of 'An investigation of two real time machine learning techniques that could enhance the adaptability of game AI agents'. Together they form a unique fingerprint.

  • Cite this

    King, D. J., & Bennett, C. (2016). An investigation of two real time machine learning techniques that could enhance the adaptability of game AI agents. In H. Barabas (Ed.), Proceedings of GAMEON'2016: the 17th International Conference on Intelligent Games and Simulation (pp. 41-48). EUROSIS.