Efficient Natural Evolution Strategies Evolution Strategies and Evolutionary Programming Track
Yi Sun, Daan Wierstra, Tom Schaul, Jürgen Schmidhuber Idsia · 2009
Efficient Natural Evolution Strategies (eNES) is a novel al-ternative to conventional evolutionary algorithms, using the natural gradient to adapt the mutation distribution. Unlike previous methods based on natural gradients, eNES uses a fast algorithm to calculate the inverse of the exact Fisher in-formation matrix, thus increasing both robustness and per-formance of its evolution gradient estimation, even in higher dimensions. Additional novel aspects of eNES include opti-mal fitness baselines and importance mixing (a procedure for updating the population with very few fitness evaluations). The algorithm yields competitive results on both unimodal and multimodal benchmarks.