evolvingfridge

As usual your references to publications is exactly what I needed to read, thank you! Are fitness landscape and fractured decision space same a problem? (I think at least they...

I think link works now. I am probably wrong and was not clear what I meant in my previews comment, but for complex environment such as soccer game, fitness function...

Did you look at different implementation of XOR and Single pole examples ?

More example are in separate repo: https://github.com/CodeReclaimers/neat-python-examples

I want to contribute but fail to understand fallowing: What is advantage and purpose of using python multi-processing when experiment requires large scale simulation, when MPI solves this issue much...

@drallensmith, MB-HyperNeat is very interesting, but why use MB-HyperNeat and not multiple MM-NEAT or RBF-NEAT combining multiple NEAT can be achieved in many ways not only by using HyperNeat. What...

It looks like your issue is with fitness function. I would try something simpler, like max distance traveled per each generation.

@puneets2811 Each genome (Car) before crash will travel N meters forward (+) or backward (-), genomes with highest positive distance traveled are your best genomes that are selected for reproduction...

- Is CTRNN a LSTM network ? - There expected some changes in near future that would allow to setup networks manually as of set static nodes/connections and mutable space,...

Interesting, I need to look more into neural networks, I spend so much time on evolution/mutation never got a chance to looks into details of neurons. Personally I am not...