Jump to content

  • Log In with Google      Sign In   
  • Create Account


Member Since 02 Jan 2002
Offline Last Active Aug 27 2014 04:32 PM

#5175302 How to make a AI choose?

Posted by IADaveMark on 21 August 2014 - 10:32 AM

"Utility" > "fuzzy"



I approve of this.

#5173444 How to make a AI choose?

Posted by IADaveMark on 13 August 2014 - 04:43 PM

Enter utility-based AI.

#5171945 Turn Based AI Technics

Posted by IADaveMark on 06 August 2014 - 03:15 PM


enter utility systems.


Any reading suggestions to get a quick overview how utility based systems differ from behaviour trees with "smart" metric-driven transitions?


Someone else tell him, please. It's less awkward that way.

#5171046 avoid ships colliding?

Posted by IADaveMark on 02 August 2014 - 12:27 AM

Cue Craig Reynolds

#5170511 Turn Based AI Technics

Posted by IADaveMark on 30 July 2014 - 11:31 PM

Re neural networks: FFS

Re BTs: most turn-based games are going to have such a complex potential solution space that BTs will break under the weight


You need something that will evaluate your potential actions in a reasonable, yet tunable way... enter utility systems.

#5169665 Adding some variation to AI

Posted by IADaveMark on 27 July 2014 - 11:57 PM

The simplest answer is what Lithander mentioned. By including random delays, you accelerate the chaos theory that Jeffery is getting at (that little difference will eventually expand into bigger ones). The other thing to do is weighted randoms where, after scoring actions or doing whatever it is you do to select, you pick from the top N actions either completely at random or by weighting them according to their score.

#5168802 some stuff about robots

Posted by IADaveMark on 23 July 2014 - 10:36 PM

Dude... you just need to stop. Seriously.

#5161755 Creating Adaptive AI in Unity

Posted by IADaveMark on 20 June 2014 - 10:40 AM



You could have "started a discussion" without 90% of your post being about your stuff.

#5156954 Human-like Chess AI

Posted by IADaveMark on 30 May 2014 - 08:55 AM

Don't think of it in terms of "adding random blunders" and instead think of it in terms of "allowing sub-optimal moves". Humans are rarely perfectly rational or optimal. By including things such as weighted random selection (not random... weighted random that still biases towards the better moves) you allow for "reasonable" moves without always being purely optimal ones.

#5146640 [Flocking] Avoid many "sub-flocks" in Cohesion

Posted by IADaveMark on 12 April 2014 - 11:49 PM

It's pretty much mathematically provable that over time, your flocks will break into groups that are proportional to some degree with your k value. It's self-reinforcing. 


One method is to not use a hard-cap on k -- but rather use all neighbors within distance d. It's a subtle difference, but I think it would help.

#5130079 human intelligence

Posted by IADaveMark on 09 February 2014 - 08:57 AM

OMG... this is still going on...


As for comparing calculation speed, go look up NP-Hard. Humans do better on NP-Hard problems because we get close enough. We estimate and parse to a point. We don't try to solve the optimal solution to the problem like a computer would tend to algorithmicaly do.


We also understand the concept of futility... we simply give up after a while.


Well... at least people not in this thread do.

#5126544 human intelligence

Posted by IADaveMark on 26 January 2014 - 12:09 PM

I just scrolled through this thread and, after seeing the amount of derpage in it, I think the OP may be on to something. Perhaps computers can equal the intelligence of SOME people in a few years, but certainly not MOST people.

#5119533 Design of AI for my Game

Posted by IADaveMark on 27 December 2013 - 12:09 PM

Is the point of this exercise to create the best player or to use neural networks? Those 2 aren't necessarily the same.

#5117229 CSP Map Coloring

Posted by IADaveMark on 15 December 2013 - 10:20 PM

This sounds suspiciously like homework... which is against the GDNet forum rules.

#5111830 How hard is AI

Posted by IADaveMark on 25 November 2013 - 08:03 AM

AI is as hard as how hard you make your AI.