Artificial neural networks can potentially control autonomous robots, vehicles, factories, or
game players more robustly than traditional approaches. Neuroevolution, ie the artificial …

An important question in neuroevolution is how to gain an advantage from evolving neural
network topologies along with weights. We present a method, NeuroEvolution of …

Two major goals in machine learning are the discovery and improvement of solutions to
complex problems. In this paper, we argue that complexification, ie the incremental …

Neuroevolution is currently the strongest method on the pole-balancing benchmark
reinforcement learning tasks. Although earlier studies suggested that there was an …

Much of recent machine learning has focused on deep learning, in which neural network
weights are trained through variants of stochastic gradient descent. An alternative approach …

The idea of using evolutionary computation to train artificial neural networks, or
neuroevolution (NE), for reinforcement learning (RL) tasks has now been around for over 20 …

Many complex control problems are not amenable to traditional controller design. Not only is
it difficult to model real systems, but often it is unclear what kind of behavior is required …

Many complex control problems require sophisticated solutions that are not amenable to
traditional controller design. Not only is it difficult to model real world systems, but often it is …

Evolving the weights of learning networks through evolutionary computation
(neuroevolution) has proven scalable over a range of challenging Reinforcement Learning …

Evolution of neural networks, or neuroevolution, has been a successful approach to many
low-level control problems such as pole balancing, vehicle control, and collision warning …