What is the relation between NEAT and reinforcement learning?

Question

As far as I know, NEAT (NeuroEvolution of Augmenting Topologies) is an algorithm that uses the concept of evolution to train a neural network. On the other hand, reinforcement learning is a type of machine learning with the concept of "rewarding" more successful nodes.

What is the difference between these two fields as they seem to be quite similar? Or is NEAT derived from reinforcement learning?

Answer 1

NeuroEvolution of Augmenting Topologies (NEAT) is a kind of Genetic Algorithm for the generation of developing artificial neural networks. It is a neuroevolution technique that alters both the weighting parameters and structures of networks, attempting to find a balance between the fitness of evolved solutions and their diversity. Reinforcement learning is about agents, learning policies to perform well in the environment. Thus they solve a different, more complex problems. Theoretically, you could learn NEAT using RL, as you might pose the problem of "given a neural network as a state, learn how to modify it over time to get better performance".