Learning to Evolve
This addresses the challenge of enhancing evolutionary optimization for researchers and practitioners, though it is incremental as it builds on existing methods.
The paper tackles the problem of improving evolutionary algorithms by learning to mutate and recombine better than random, using deep reinforcement learning to dynamically adjust strategies, resulting in outperforming classical evolutionary algorithms on combinatorial and continuous optimization problems.
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.