Evolving Through the Looking Glass

We show how generative machine learning can learn a representation corresponding to a valid region of search space, enabling optimizers to search in the new latent space and always find solutions that satisfy constraints or additional criteria. This work continues previous work and demonstrates the method for more complex constraints and additional criteria.

Abstract

Evolving Through the Looking Glass: Learning Improved Search Spaces with Variational Autoencoders.

Bentley, P. J., Lim, S. L., Gaier, A. and Tran, L.

Parallel Problem Solving From Nature (PPSN) 2022

Nature has spent billions of years perfecting our genetic representations, making them evolvable and expressive. Generative machine learning offers a shortcut: learn an evolvable latent space with implicit biases towards better solutions. We present SOLVE: Search space Optimization with Latent Variable Evolution, which creates a dataset of solutions that satisfy extra problem criteria or heuristics, generates a new latent search space, and uses a genetic algorithm to search within this new space to find solutions that meet the overall objective. We investigate SOLVE on five sets of criteria designed to detrimentally affect the search space and explain how this approach can be easily extended as the problems become more complex. We show that, compared to an identical GA using a standard representation, SOLVE with its learned latent representation can meet extra criteria and find solutions with distance to optimal up to two orders of magnitude closer. We demonstrate that SOLVE achieves its results by creating better search spaces that focus on desirable regions, reduce discontinuities, and enable improved search by the genetic algorithm.