hello world

  • 7 Replies
  • 3983 Views
*

rottjung

  • Roomba
  • *
  • 17
hello world
« on: August 04, 2015, 01:05:32 pm »
hey
I teach Game Development (Programming C#) at MAD Faculty in Belgium.
I started this summer with AI, mainly Neural Nets.
Now trying my first Genetic Algorithm.

here's a sim i did with using a Monty hall type of choosing as input for a ANN.
there are 3 actions to choose from: Eat, Kill, Procreate.
it chooses one of these based on the Monty Hall Problem.
It sends the choice to the neural network, together with the current balance of the environment (i.e. food/population). The net reviews the choice and its impact on the environment and rewards or punishes a decision depend on that impact.
Longest run i did was +2.600.000 generations :) so i guess it can go on for ever...
https://dl.dropboxusercontent.com/u/32556668/MontyHallANN.html

guess I'm looking for a community to get some feedback ;-)
cheers
J.

*

ivan.moony

  • Trusty Member
  • ************
  • Bishop
  • *
  • 1729
    • mind-child
Re: hello world
« Reply #1 on: August 04, 2015, 02:49:19 pm »
Hello Rottjung :)

I'm sorry, but required Unity is not available for my Linux.
« Last Edit: August 04, 2015, 03:18:00 pm by ivan.moony »

*

rottjung

  • Roomba
  • *
  • 17
Re: hello world
« Reply #2 on: August 04, 2015, 05:16:14 pm »
should you really want to see it  :)
http://wiki.unity3d.com/index.php/Running_Unity_Web_Player_on_Linux_using_Pipelight
i use unity as it is a fast and simple way to visualize and interface a program...

*

Freddy

  • Administrator
  • **********************
  • Colossus
  • *
  • 6860
  • Mostly Harmless
Re: hello world
« Reply #3 on: August 04, 2015, 05:51:17 pm »
Hi and welcome to AiDreams  :)

I use Unity myself, I'm hoping WebGL will take over with that, I have tried a couple of times but so far Firefox seems to work best with Unity stuff.
« Last Edit: August 04, 2015, 06:39:48 pm by Freddy »

*

rottjung

  • Roomba
  • *
  • 17
Re: hello world
« Reply #4 on: August 04, 2015, 06:05:34 pm »
thx Freddy,
I'm on mac with chrome, no trouble so far but i do believe chrome's support for the unity player will be ended in the near future.

*

Freddy

  • Administrator
  • **********************
  • Colossus
  • *
  • 6860
  • Mostly Harmless
Re: hello world
« Reply #5 on: August 04, 2015, 06:42:13 pm »
Yep it's due to Google dropping the aged npapi thing.

There's no point developing for Chrome using a web player now really, unless people are on older versions of course and they intend to stay on them.

Best to move on.

*

Art

  • At the end of the game, the King and Pawn go into the same box.
  • Trusty Member
  • **********************
  • Colossus
  • *
  • 5865
Re: hello world
« Reply #6 on: August 05, 2015, 11:44:31 pm »
Welcome Rottjung!

Hope you enjoy your stay with us.

I ran your sim and noticed the number of "units" seems to remain "balanced" between 23 to 40 depending on which activity they happen to be engaged in at the moment.

A lot of the action / changes happen rather quickly and it takes a few moments for one to get the gist of what's transpiring.

Nice demo and interesting project.

Perhaps a method to reward the ones who eat, procreate and then go one to become a stronger, bigger unit/character.
Might be difficult to keep the bully syndrome from kicking in or taking over but at any rate it would be interesting to watch.

Anyhow, welcome and keep up the good work!
In the world of AI, it's the thought that counts!

*

rottjung

  • Roomba
  • *
  • 17
Re: hello world
« Reply #7 on: August 06, 2015, 01:20:18 pm »
hey Art,
thanks for trying :-)
yes you can up the population by increasing the food supplied.
It was just a test for the monty hall problem, although I'm not sure if it is relevant once the neural net starts adjusting bias toward a needed action.
I was actually looking for a very very simple way of implementing a probability field, "inspired" by heisenberg uncertainty principle: that with the most chance of happening will happen, until then everything can happen...
so with monty hall i tried looking at it as if every door holds a 1 and a 0 until you open up one, if it's not 1 the other doors chances increase...

 


Will LLMs ever learn what is ... is?
by HS (Future of AI)
November 10, 2024, 06:28:10 pm
Who's the AI?
by frankinstien (Future of AI)
November 04, 2024, 05:45:05 am
Project Acuitas
by WriterOfMinds (General Project Discussion)
October 27, 2024, 09:17:10 pm
Ai improving AI
by infurl (AI Programming)
October 19, 2024, 03:43:29 am
Atronach's Eye
by WriterOfMinds (Home Made Robots)
October 13, 2024, 09:52:42 pm
Running local AI models
by spydaz (AI Programming)
October 07, 2024, 09:00:53 am
Hi IM BAA---AAACK!!
by MagnusWootton (Home Made Robots)
September 16, 2024, 09:49:10 pm
Attempting Hydraulics
by MagnusWootton (Home Made Robots)
August 19, 2024, 04:03:23 am
LLaMA2 Meta's chatbot released
by spydaz (AI News )
August 24, 2024, 02:58:36 pm
ollama and llama3
by spydaz (AI News )
August 24, 2024, 02:55:13 pm
AI controlled F-16, for real!
by frankinstien (AI News )
June 15, 2024, 05:40:28 am
Open AI GPT-4o - audio, vision, text combined reasoning
by MikeB (AI News )
May 14, 2024, 05:46:48 am
OpenAI Speech-to-Speech Reasoning Demo
by MikeB (AI News )
March 31, 2024, 01:00:53 pm
Say good-bye to GPUs...
by MikeB (AI News )
March 23, 2024, 09:23:52 am
Google Bard report
by ivan.moony (AI News )
February 14, 2024, 04:42:23 pm
Elon Musk's xAI Grok Chatbot
by MikeB (AI News )
December 11, 2023, 06:26:33 am

Users Online

459 Guests, 0 Users

Most Online Today: 571. Most Online Ever: 2369 (November 21, 2020, 04:08:13 pm)

Articles