Learning to Evolve

TL;DR

This paper demonstrates that using deep reinforcement learning to adaptively learn mutation and recombination strategies enhances the efficiency and effectiveness of evolutionary algorithms in optimization tasks.

Contribution

It introduces a method where learning guides evolution, improving mutation and recombination processes over traditional random approaches.

Findings

Learned strategies outperform classical algorithms in fitness improvement.

Adaptive methods achieve higher attainable fitness levels.

Deep reinforcement learning effectively guides evolutionary processes.

Abstract

Evolution and learning are two of the fundamental mechanisms by which life adapts in order to survive and to transcend limitations. These biological phenomena inspired successful computational methods such as evolutionary algorithms and deep learning. Evolution relies on random mutations and on random genetic recombination. Here we show that learning to evolve, i.e. learning to mutate and recombine better than at random, improves the result of evolution in terms of fitness increase per generation and even in terms of attainable fitness. We use deep reinforcement learning to learn to dynamically adjust the strategy of evolutionary algorithms to varying circumstances. Our methods outperform classical evolutionary algorithms on combinatorial and continuous optimization problems.