Archived

This topic is now archived and is closed to further replies.

Case Based Reasoning (CBR) in Games

This topic is 5335 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

Recommended Posts

Hi, I want to use decent CBR routines in a game I wrote. I know the theory about CBR''s well and also do know about some implementations in other fields... But I haven''t found a single hint that a single game used CBR-routines although there are some papers out there about the advantages this method would offer for games... So I would like to know if anybody here already used CBRs for AI-programming or if anybody knows of projects using them ... already the smallest hint will be helpfull ...

Share this post


Link to post
Share on other sites
quote:
Original post by smarechal
I dont''t know exactly what case based reasoning is but to me it sounds mighty similar to Finite State Machines. Maybe you could look those up and see if that''s what you need.
Why the heck would you think it is like Finite State Machines? Explore my sig. Especially SWALE.



_______________________________

"To understand the horse you''ll find that you''re going to be working on yourself. The horse will give you the answers and he will question you to see if you are sure or not."
- Ray Hunt, in Think Harmony With Horses


ALU - SHRDLU - WORDNET - CYC - SWALE - AM - CD - J.M. - K.S. | CAA - BCHA - AQHA - APHA - R.H. - T.D. | 395 - SPS - GORDIE - SCMA - R.M. - G.R. - V.C. - C.F.

Share this post


Link to post
Share on other sites
quote:
Original post by bishop_pass
Why the heck would you think it is like Finite State Machines?
Because I never heard of CBR and the original poster couldn''t find implementations in games. I figured that in GD land we might call them FSM instead. The name implied the same to me (if a case or state is set, do some predefined reasoning e.g. a pattern of some sort).

Guess I was wrong



Sander Maréchal
[Lone Wolves Game Development][RoboBlast][Articles][GD Emporium][Webdesign][E-mail]

Share this post


Link to post
Share on other sites
Well sorry to be not precise but I thought that CBR is well known ...
The AAAI already proposed them to be used in game for there learning possibilities and cause they offer so much more than e.g. A* or FSM ...
so you can use A* if the situation is clear and you can calculate easyly the effacts of all your actions (TicTacToe) ... CBR take unclear (e.g. fuzzy) values instead to choose from a list of known cases which is closest to the needed case ... then the algorithm will try to use the solution for the given case by adapting the old solution to the new case. If this atempt was succesfull the new solution is generally saved in the case databaseas a new sample of acting ...
So the advantage of CBR''s in games is clear: You need a startup database for many situations but while using this database the theory (and practical implementations like google) show that the system will realy learn/improove ...

Share this post


Link to post
Share on other sites