|
|
|
 |

February 14th, 2002, 03:12 PM
|
 |
Colonel
|
|
Join Date: Jan 2001
Posts: 1,661
Thanks: 0
Thanked 0 Times in 0 Posts
|
|
Re: AI longtime simulation feature
Me too I would welcome such a AI longtime simulation possibility.
|

February 15th, 2002, 09:33 PM
|
 |
First Lieutenant
|
|
Join Date: Mar 2001
Location: Bordesholm, Germany
Posts: 781
Thanks: 6
Thanked 0 Times in 0 Posts
|
|
Re: AI longtime simulation feature
quote: Originally posted by Shyrka:
The idea is very good, not only for modders but also to MM. Why not "train" the AI to improve it just as neural nets, decision trees or other algorithms? (In these structures engineers run a situation and lets the system deal with it, so they learn from them errors. With time the systems take better and better decisions).
Hey Shyrka, do you know "Fritz", my favorite chess program ? It has a self-optimizing engine which does not make the same error for a second time.
For SEIV this would be future music, but what a potential ! EDIT: "dreams of the future", of course. I am still thinking too much in german.
Regards from a dreaming PTF...
[ 15 February 2002: Message edited by: PsychoTechFreak ]
|

February 16th, 2002, 01:50 PM
|
Corporal
|
|
Join Date: Oct 2001
Location: La Coruña, Spain
Posts: 112
Thanks: 0
Thanked 0 Times in 0 Posts
|
|
Re: AI longtime simulation feature
quote: Originally posted by PsychoTechFreak:
Hey Shyrka, do you know "Fritz", my favorite chess program ? It has a self-optimizing engine which does not make the same error for a second time.[ 15 February 2002: Message edited by: PsychoTechFreak ]
Really? Then that's exactly what I was thinking. SE4 is so deep that for making the AI more effective some training algorithm is needed.
Any "Fritz" related web page? 
__________________
So it shall be written...
So it shall be done...
--------------------
|

February 17th, 2002, 10:04 AM
|
 |
First Lieutenant
|
|
Join Date: Mar 2001
Location: Bordesholm, Germany
Posts: 781
Thanks: 6
Thanked 0 Times in 0 Posts
|
|
Re: AI longtime simulation feature
quote: Originally posted by Shyrka:
Any "Fritz" related web page?
Sure,
http://www.chessbase.com/catalog/product.asp?pid=85
I don't have the ver 7, this has been published just recently ,I have got ver 6, the older Versions are a lot cheaper.
|

February 17th, 2002, 04:58 PM
|
 |
Colonel
|
|
Join Date: Jul 2000
Location: Montevideo Uruguay
Posts: 1,598
Thanks: 0
Thanked 0 Times in 0 Posts
|
|
Re: AI longtime simulation feature
quote: Originally posted by Shyrka:
Really? Then that's exactly what I was thinking. SE4 is so deep that for making the AI more effective some training algorithm is needed.
Any "Fritz" related web page?
Saludos Chaval!
Hey, I agree 100% with you... but sadly, this never will be for SE4. But I hope that SEV or SEVI (or something other 4X game!), will have an AI with learning capabilities some day.
|

March 14th, 2002, 12:21 AM
|
 |
First Lieutenant
|
|
Join Date: Mar 2001
Location: Bordesholm, Germany
Posts: 781
Thanks: 6
Thanked 0 Times in 0 Posts
|
|
Re: AI longtime simulation feature
Do you know what ? I have found an interim solution:
-set up a game with cheat codes allowed
-quick research shields until system grav. shield facility, with the "money" cheat
-quick research stellar manipulation until gravitational condensor
-close all warp points to your home system(s)
-build a system grav. shield
-Under Empire Options: turn off "show log at start of turn", and turn off "display confirmation dialog when ending turn"
And then put your coffee mug onto your F12 key...
Next morning: Release F12.
But an additional savegame with increasing indices every 10 or 20 turns would be nice (idea of Rollo, we had a short discussion about this).
|

March 14th, 2002, 01:02 AM
|
 |
First Lieutenant
|
|
Join Date: Mar 2001
Location: Bordesholm, Germany
Posts: 781
Thanks: 6
Thanked 0 Times in 0 Posts
|
|
Re: AI longtime simulation feature
...but the random events should be considered, either you use the Lucky trait or turn off the events completely. Most times I turn off the events and the ruins also in longterm sims because the impact is sometimes too much for a comparison (e.g. I saw a weak race which found another colony tech in a ruin and all of a sudden the score ran beyond the roof).
|
Posting Rules
|
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts
HTML code is On
|
|
|
|
|