Welcome Guest [Log In] [Register]
We hope you enjoy your visit.


You're currently viewing the Ultimate 3D Community as a guest. This means that you can only read posts, but can not create posts or topics by yourself. To be able to post you need to register. Then you can participate in the community active and use many member-only features such as customizing your profile, sending personal messages, and voting in polls. Registration is simple, fast, and completely free.

Join our community!

If you are already a member please log in to your account to access all of our features:

Username:   Password:
Add Reply
AI
Topic Started: Jul 12 2013, 05:17 PM (194 Views)
DJ-Habana
C# King
[ *  *  *  *  *  * ]
Ok, my current subject we have at campus is advanced research.
Our project is a 30 page thesis, each student get a different topic and my topic is
"Artificial Intelligence in Game Programming is a Complex and a challenge for programmers to achieve the goal for the AI to do decisions when its coming to attacking or defending. Can this algorithm be simplified"

Things to consider :
1) What units to build
2) How many units to build for maximum damage
3) Limited resources


Ok so my problem is not solving that I already have my own way to do this, but our lecturer said we must do a comparison with at least 4 methods to do this.
Can anyone refer me to a website or article about this specific area in AI
Posted Image


Offline Profile Quote Post Goto Top
 
Gandalf20000
Member Avatar
Geek
[ *  *  *  *  *  * ]
So you're talking about an optimization problem? I did something similar (on a much smaller and simpler scale, of course) for a research project this year. You might consider using some basic machine learning techniques such as neural networking, reinforcement learning, genetic algorithms, or a combination of these methods. There are tons of papers published online that talk about these things. Just do a search for "AI optimization techniques," "Machine learning," or something similar. You also might consider a more mathematical approach to your optimization (depending on the complexity, of course) as opposed to some more trial-and-error oriented approaches.
Offline Profile Quote Post Goto Top
 
DJ-Habana
C# King
[ *  *  *  *  *  * ]
Gandalf20000
Jul 12 2013, 05:44 PM
So you're talking about an optimization problem? I did something similar (on a much smaller and simpler scale, of course) for a research project this year. You might consider using some basic machine learning techniques such as neural networking, reinforcement learning, genetic algorithms, or a combination of these methods. There are tons of papers published online that talk about these things. Just do a search for "AI optimization techniques," "Machine learning," or something similar. You also might consider a more mathematical approach to your optimization (depending on the complexity, of course) as opposed to some more trial-and-error oriented approaches.
Cool thank you, I will doing my research, my approach I am going to use is check if Linear Programming Solving can be a way to do this. Have an Idea to do it
Posted Image


Offline Profile Quote Post Goto Top
 
DJ-Habana
C# King
[ *  *  *  *  *  * ]
I never gave my result of this research assignment,

I had 98%. only issues that they had was I did not include terain type constraints to the units thus they say If it was a battle over the ocean only ships and planes may be used,
Damn campus only looked for excuse to not give a 100% :P
Posted Image


Offline Profile Quote Post Goto Top
 
« Previous Topic · Off-topic · Next Topic »
Add Reply