Evolvability ES: Scalable and Direct Optimization of Evolvability
This addresses the problem of accelerating evolution and enabling fast adaptation in evolutionary algorithms for researchers in machine learning and evolutionary computation, offering a novel approach with competitive performance against gradient-based methods like MAML.
The paper tackles the challenge of designing evolutionary algorithms that optimize for evolvability, introducing evolvability ES to maximize behavioral diversity under mutations, and demonstrates its ability to generate solutions with tens of thousands of parameters that adapt quickly to different tasks and seed further evolution.
Designing evolutionary algorithms capable of uncovering highly evolvable representations is an open challenge; such evolvability is important because it accelerates evolution and enables fast adaptation to changing circumstances. This paper introduces evolvability ES, an evolutionary algorithm designed to explicitly and efficiently optimize for evolvability, i.e. the ability to further adapt. The insight is that it is possible to derive a novel objective in the spirit of natural evolution strategies that maximizes the diversity of behaviors exhibited when an individual is subject to random mutations, and that efficiently scales with computation. Experiments in 2-D and 3-D locomotion tasks highlight the potential of evolvability ES to generate solutions with tens of thousands of parameters that can quickly be adapted to solve different tasks and that can productively seed further evolution. We further highlight a connection between evolvability and a recent and popular gradient-based meta-learning algorithm called MAML; results show that evolvability ES can perform competitively with MAML and that it discovers solutions with distinct properties. The conclusion is that evolvability ES opens up novel research directions for studying and exploiting the potential of evolvable representations for deep neural networks.