Natural Evolution Strategies

— This paper presents Natural Evolution Strategies (NES), a novel algorithm for performing real-valued ‘black box’ function optimization: optimizing an unknown objective function where algorithm-selected function measurements constitute the only information accessible to the method. Natural Evolution Strategies search the fitness landscape using a multivariate normal distribution with a self-adapting mutation matrix to generate correlated mutations in promising regions. NES shares this property with Covariance Matrix Adaption (CMA), an Evolution Strategy (ES) which has been shown to perform well on a variety of high-precision optimization tasks. The Natural Evolution Strategies algorithm, however, is simpler, less ad-hoc and more principled. Self-adaptation of the mutation matrix is derived using a Monte Carlo estimate of the natural gradient towards better expected fitness. By following the natural gradient instead of the ‘vanilla’ gradient, we can ensure efficient update...

• Type: Conference
• Year: 2008
• Where: CEC
• Authors: Daan Wierstra, Tom Schaul, Jan Peters, Jürgen Schmidhuber
• Keywords: Artificial Intelligence, CEC 2008, Mutation Matrix, Natural Evolution Strategies, Self-adapting Mutation Matrix