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

06/16/2021
by   Kevin Frans, et al.
0

Inspired by natural evolution, evolutionary search algorithms have proven remarkably capable due to their dual abilities to radiantly explore through diverse populations and to converge to adaptive pressures. A large part of this behavior comes from the selection function of an evolutionary algorithm, which is a metric for deciding which individuals survive to the next generation. In deceptive or hard-to-search fitness landscapes, greedy selection often fails, thus it is critical that selection functions strike the correct balance between gradient-exploiting adaptation and exploratory diversification. This paper introduces Sel4Sel, or Selecting for Selection, an algorithm that searches for high-performing neural-network-based selection functions through a meta-evolutionary loop. Results on three distinct bitstring domains indicate that Sel4Sel networks consistently match or exceed the performance of both fitness-based selection and benchmarks explicitly designed to encourage diversity. Analysis of the strongest Sel4Sel networks reveals a general tendency to favor highly novel individuals early on, with a gradual shift towards fitness-based selection as deceptive local optima are bypassed.

READ FULL TEXT
research
03/28/2012

On the Easiest and Hardest Fitness Functions

The hardness of fitness functions is an important research topic in the ...
research
12/06/2019

Information-geometric optimization with natural selection

Evolutionary algorithms, inspired by natural evolution, aim to optimize ...
research
07/29/2015

On Proportions of Fit Individuals in Population of Evolutionary Algorithm with Tournament Selection

In this paper, we consider a fitness-level model of a non-elitist mutati...
research
07/13/2019

Evolvability ES: Scalable and Direct Optimization of Evolvability

Designing evolutionary algorithms capable of uncovering highly evolvable...
research
09/16/2011

Roulette-wheel selection via stochastic acceptance

Roulette-wheel selection is a frequently used method in genetic and evol...
research
10/24/2018

Semantic Neutral Drift

We introduce the concept of Semantic Neutral Drift (SND) for evolutionar...
research
04/09/2018

A theory of consciousness: computation, algorithm, and neurobiological realization

The most enigmatic aspect of consciousness is the fact that it is felt, ...

Please sign up or login with your details

Forgot password? Click here to reset