Jump to content

  • Log In with Google      Sign In   
  • Create Account


rouncer

Member Since 21 Nov 2005
Offline Last Active Today, 11:21 AM
*----

Posts I've Made

In Topic: State Machine

Yesterday, 01:22 PM

forgive me if everyone already knows this :), I typed this out before I read enough of the posts, but I like it so im going to leave it.

 

I think really generally about things, and state machine, behaviour tree, scoring program,  they all do the same thing, they are a commander, you do them all slightly different ways I guess.

 

Even an adaptive self programming robot has a state machine or something like it, controlling his global will, so they are cool, just they handle the actual way to achieve the broader goal, and the low level implementation is left variable for it to work out the exact way to win given the circumstance.  Thats what im into at the moment.

 

The state machine you have to write has to include every minute detail of implementation,  but a cool way to do it, is to leave the actual low level code to a call from the main supervisor,  like so:   

 

 

MAIN SUPERVISOR  ->  if(happy) walk to blue light,  if(sad) walk to green light

                                     

SECONDARY LEVEL -> find position of thing walking to, send to movement code.

 

MOVEMENT CODE -> deal with obstacles, move legs over tough terrain, and get to the position.

 

 

Breaking it up into modules makes a really hard job easier, especially if you worked for NASA, making some automonous planet rover.

A self programming bot isnt really necessary, a manually coded one works fine, and uses a much smaller processor, but as im into ai hardcore, its a more worthwhile goal to me.


In Topic: specialistism?

07 July 2014 - 05:12 AM

how many programmers even know how ac current works, from the magnet to the transformer to the diodes.   and quantum physics, i know nothing about, if I thought anything about Einstien's theory id be completely without any standard of knowledge to contest anything.  You forgot how important it was to be a plumber, not all this high level c code that depends on the entire development of technology I know nothing about.


In Topic: Gamedev video log (youtube)

06 July 2014 - 10:02 AM

keep going, looks pretty cool. these things take SO MUCH WORK!! arrrrr


In Topic: What gets you motivated to code?

06 July 2014 - 09:56 AM

Part of your creative repertoire, is being able to come up with programs that are fun, interesting, with a small code base... like flappy bird I guess, but obviously something new and novel that hasn't been done or failing that it comes to making modules that are interesting in themselves, that could be a part of a whole, if you get that far.

 

AI fits that category, I think, Simple neural nets don't have to be that big, especially if they just based upon random development, and that is what I'm doing that the moment, even though mines looking like 20 functions, once all the local minima/maxima is detecting it may be pretty big, but I don't mind, because I've been planning it for so long (I can remember thinking about it 4 years ago), and desperation is going to lead me to finally finish it.

 

When Ectara said despair, I'm afraid sometimes that's the truth.  No pain, no gain.


In Topic: AI for continuous snake game (trying NEAT algorithm)

24 June 2014 - 09:42 PM

i (as in myself) wouldnt use neat, i dont believe in genetic algorythms.

 

What I would do, is put some "sight" into a set of inputs, like your doing now, with those hairs,  its best it always knew where the opponent was, maybe even what part of the screen he was.  the difficult thing would hes only aware of some of the lines there.

 

If youd like to do it like this yet still speculation of mine ->

 

now youve got that,  just randomize a function that leads to left and right directions.

 

ok, if you do that, youll have to wait ten million years for him to learn a single step,  cause you cant justify any of its learning yet.   its based apon success of wins, so youd have to wait for a whole game to finish to even judge a single randomization.

 

what you have to do is form a rule for your play, in the form of a function watching your outputs, but giving you the sight that he has,  cause he pretends you play like him, except you cheat and see the whole thing in detail.

 

ok, to actually justify the mutation, you have to play games in high speed of him, and the function that is "dummying" you,  the more you speed it up the quicker hell be able to justify its behaviour as successful or a failure.  the length of time it takes for him to lose or win (on a pole) would be how you would score it.


PARTNERS