Population-Based Evolution Optimizes a Meta-Learning Objective

03/11/2021
by   Kevin Frans, et al.
0

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.

READ FULL TEXT

page 5

page 6

page 7

research
03/16/2023

Arbitrary Order Meta-Learning with Simple Population-Based Evolution

Meta-learning, the notion of learning to learn, enables learning systems...
research
07/13/2019

Evolvability ES: Scalable and Direct Optimization of Evolvability

Designing evolutionary algorithms capable of uncovering highly evolvable...
research
09/29/2021

Dynamic Regret Analysis for Online Meta-Learning

The online meta-learning framework has arisen as a powerful tool for the...
research
01/01/2022

Distributed Evolution Strategies Using TPUs for Meta-Learning

Meta-learning traditionally relies on backpropagation through entire tas...
research
05/21/2021

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...
research
11/13/2020

Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning

Recent work has shown promising results using Hebbian meta-learning to s...
research
10/07/2022

Learning to Learn and Sample BRDFs

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

Please sign up or login with your details

Forgot password? Click here to reset