It is NEAT but the weights are trained with Natural Evolution Strategy and the weights are shared across genomes.
numpy
cloudpickle
pip install nesneat
matplotlib # To draw networks
mpi4py # For parallelization
gym # For examples
Check examples
PYTHONPATH="$(pwd):$PYTHONPATH" python examples/cartpole.py
# Or in parallel
PYTHONPATH="$(pwd):$PYTHONPATH" mpirun -np 2 python examples/cartpole.py