Evolvability ES: Scalable and Direct Optimization of Evolvability

by   Alexander Gajewski, et al.

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.


Population-Based Evolution Optimizes a Meta-Learning Objective

Meta-learning models, or models that learn to learn, have been a long-de...

Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning

Learning adaptable policies is crucial for robots to operate autonomousl...

Selecting for Selection: Learning To Balance Adaptive and Diversifying Pressures in Evolutionary Search

Inspired by natural evolution, evolutionary search algorithms have prove...

Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts

Evolutionary algorithms have been used in the digital art scene since th...

Distributed Evolution Strategies Using TPUs for Meta-Learning

Meta-learning traditionally relies on backpropagation through entire tas...

VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution

Recent advances in deep neuroevolution have demonstrated that evolutiona...

Please sign up or login with your details

Forgot password? Click here to reset