MiniRTS - Strategy Identification using Bayesian Grid Models
Student thesis: Master Thesis and HD Thesis
- Mads Dancker-Jensen
4. term, Software, Master (Master Programme)
This report describes the investigation
of using Bayesian Grid
Models for reasoning in RTS
games.
The first part of this report documents the implementation of the environment used to study the performance of the Bayesian Grid Model. The environment is a RTS game called MiniRTS which is similar to the commercial games but has been simplified to fit the purposes of this project best.
In the experimentation phase of the project, different scenarios have been created with the purpose of comparing different models to see which factors could improve the performance.
Finally the report concludes and evaluates upon the results, and describes which improvements could be made in the future.
The first part of this report documents the implementation of the environment used to study the performance of the Bayesian Grid Model. The environment is a RTS game called MiniRTS which is similar to the commercial games but has been simplified to fit the purposes of this project best.
In the experimentation phase of the project, different scenarios have been created with the purpose of comparing different models to see which factors could improve the performance.
Finally the report concludes and evaluates upon the results, and describes which improvements could be made in the future.
Language | English |
---|---|
Publication date | Aug 2008 |