In strategy-based games, it is sometimes beneficial to understand the evaluation processes of the game AI opponent, e.g. What strategic or tactical motives is it inferring? Why did it make the previous move? However, the mechanics available to allow the game AI to convey these processes to the [human] player or game designer is complex to implement, more so than the actual mechanics of the game AI itself. This paper proposes a method that provides the mechanism for a game AI to communicate its evaluation processes using descriptive schemata and explanatory functions. A case study will be presented that includes an implementation of a game AI opponent that is capable of describing its inferential processes while playing a tabletop wargame.
Funding
Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)
History
Parent Title
DIMEA 2007 : 2nd International Conference on Digital Interactive Media in Entertainment and Arts, 5-7 September 2007, Perth, Western Australia.