Date of Award


Publication Type

Doctoral Thesis

Degree Name



Computer Science

First Advisor

Goodwin, Scott (Computer Science)


Computer science.



Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.


Forming effective team strategies using heterogeneous agents to accomplish a task can be a challenging problem. The number of combinations of actions to look through can be enormous, and having an agent that is really good at a particular sub-task is no guarantee that agent will perform well on a team with members with different abilities. Dynamic Scripting has been shown to be an effective way of improving behaviours with adaptive game AI. We present an approach that modifies the scripting process to account for the other agents in a game. By analyzing an agent's allies and opponents we can create better starting scripts for the agents to use. Creating better starting points for the Dynamic Scripting process and will minimize the number of iterations needed to learn effective strategies, creating a better overall gaming experience.