Population-Based Evolution Optimizes a Meta-Learning Objective
This work addresses the problem of costly meta-learning algorithms for researchers and practitioners, offering a more efficient approach, though it appears incremental by building on evolutionary concepts.
The paper tackles the challenge of expensive meta-learning methods by proposing that population-based evolutionary systems naturally optimize for high evolvability, which aligns with meta-learning objectives. They demonstrate this with a simple algorithm, PBML, which discovers genomes that show higher improvement rates and can quickly adapt to tasks like sparse fitness and robotic control.
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.