Paper

Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization

Schaul, Tom, Lu, Chris, Zahavy, Tom, Lange, Robert Tjarko, Chen, Yutian, Dalibard, Valentin, Flennerhag, Sebastian

2023

Overview

Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution. While they provide a general-purpose tool for optimization, their particular instantiations can be heuristic and motivated by loose biological intuition. In this work we explore a fundamentally different approach: Given a sufficiently flexible parametrization of the genetic operators, we discover entirely new genetic algorithms in a data-driven fashion. More specifically, we parametrize selection and mutation rate adaptation as cross- and self-attention modules and use Meta-Black-Box-Optimization to evolve their parameters on a set of diverse optimization tasks. The resulting Learned Genetic Algorithm outperforms state-of-the-art adaptive baseline genetic algorithms and generalizes far beyond its meta-training settings. The learned algorithm can be applied to previously unseen optimization problems, search dimensions & evaluation budgets. We conduct extensive analysis of the discovered operators and provide ablation experiments, which highlight the benefits of flexible module parametrization and the ability to transfer (`plug-in') the learned operators to conventional genetic algorithms.

• Publisher: Cornell University Library, arXiv.org
• Subject: Ablation / Adaptive algorithms / Biological evolution / Black boxes / Genetic algorithms / Modules / Operators / Optimization / Parameterization