Header logo is ei

Natural Evolution Strategies


Conference Paper


This paper presents natural evolution strategies (NES), a novel algorithm for performing real-valued dasiablack boxpsila 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 dasiavanillapsila gradient, we can ensure efficient update steps while preventing early convergence due to overly greedy updates, resulting in reduced sensitivity to local suboptima. We show NES has competitive performance with CMA on unimodal tasks, while outperforming it on several multimodal tasks that are rich in deceptive local optima.

Author(s): Wierstra, D. and Schaul, T. and Peters, J. and Schmidhuber, J.
Book Title: CEC 2008
Journal: Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2008)
Pages: 3381-3387
Year: 2008
Month: June
Day: 0
Publisher: IEEE

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1109/CEC.2008.4631255
Event Name: IEEE Congress on Evolutionary Computation
Event Place: Hong Kong, China

Address: Piscataway, NJ, USA
Digital: 0
Institution: Institute of Electrical and Electronics Engineers
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {Natural Evolution Strategies},
  author = {Wierstra, D. and Schaul, T. and Peters, J. and Schmidhuber, J.},
  journal = {Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2008)},
  booktitle = {CEC 2008},
  pages = {3381-3387},
  publisher = {IEEE},
  organization = {Max-Planck-Gesellschaft},
  institution = {Institute of Electrical and Electronics Engineers},
  school = {Biologische Kybernetik},
  address = {Piscataway, NJ, USA},
  month = jun,
  year = {2008},
  month_numeric = {6}