NEAT Visualizer

[lolz123]

Yet another update (now at 2.1), and again to the reinforcement learning! I heavily modified the previous algorithm so that it "drifts" away from undesired outputs and is "slapped" into taking the correct drift direction (there are 2 directions). There are 2 new adjustable parameters as a result, alpha for the drift speed and slapFactor for the directional slap. I have tested this new learning rule with the NEAT evolved networks as well as plain feed forward neural networks and it is able to easily learn logic gates.

[lolz123]

I posted an article describing how you can create your own AI similar to that of the NEAT Visualizer.
I know that I am not the best writer, but hopefully it is well written enough to follow 

Here it is for those interested:

http://www.gamedev.net/page/resources/_/technical/artificial-intelligence/reinforcement-learning-for-games-r3271

[lolz123]

It has been a while, but I finally made a new version (3.0) of the NEAT algorithm and its associated visualization system.

I made this new version mostly since I need it for a new AI experiment I am working on 

I have mostly just updated the code to use more modern C++.

Download link is in the original post.

I will probably eventually release a large AI library with various techniques I have come up over the years, but for now here is NEAT standalone.