Neuroevolution is a machine learning technique that applies evolutionary algorithms to construct artificial neural networks, taking inspiration from the evolution of biological nervous systems in nature. Compared to other neural network learning methods, neuroevolution is highly general; it allows learning without explicit targets, with only sparse feedback, and with arbitrary neural models and network structures. Neuroevolution is an effective approach to solving reinforcement learning problems, and is most commonly applied in evolutionary robotics and artificial life.

HTML

Scholarpedia, 8(6):30977, 2013.

@article{lehman:scholarpedia13, title={Neuroevolution}, author={Joel Lehman and Risto Miikkulainen}, volume={8}, journal={Scholarpedia}, number={6}, pages={30977}, url="http://nn.cs.utexas.edu/?lehman:scholarpedia13", year={2013} }