DeepAI AI Chat
Log In Sign Up

Population-Based Evolution Optimizes a Meta-Learning Objective

by   Kevin Frans, et al.

Meta-learning models, or models that learn to learn, have been a long-desired target for their ability to quickly solve new tasks. Traditional meta-learning methods can require expensive inner and outer loops, thus there is demand for algorithms that discover strong learners without explicitly searching for them. We draw parallels to the study of evolvable genomes in evolutionary systems – genomes with a strong capacity to adapt – and propose that meta-learning and adaptive evolvability optimize for the same objective: high performance after a set of learning iterations. We argue that population-based evolutionary systems with non-static fitness landscapes naturally bias towards high-evolvability genomes, and therefore optimize for populations with strong learning ability. We demonstrate this claim with a simple evolutionary algorithm, Population-Based Meta Learning (PBML), that consistently discovers genomes which display higher rates of improvement over generations, and can rapidly adapt to solve sparse fitness and robotic control tasks.


page 5

page 6

page 7


Arbitrary Order Meta-Learning with Simple Population-Based Evolution

Meta-learning, the notion of learning to learn, enables learning systems...

Evolvability ES: Scalable and Direct Optimization of Evolvability

Designing evolutionary algorithms capable of uncovering highly evolvable...

Eliminating Meta Optimization Through Self-Referential Meta Learning

Meta Learning automates the search for learning algorithms. At the same ...

Distributed Evolution Strategies Using TPUs for Meta-Learning

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

On the use of feature-maps and parameter control for improved quality-diversity meta-evolution

In Quality-Diversity (QD) algorithms, which evolve a behaviourally diver...

Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning

Recent work has shown promising results using Hebbian meta-learning to s...

Learning to Learn and Sample BRDFs

We propose a method to accelerate the joint process of physically acquir...