Reinforcement learning based adaptive metaheuristics

TL;DR

This paper introduces a reinforcement learning framework to automatically adapt hyperparameters in continuous optimization algorithms, demonstrating competitive results on benchmark functions for CMA-ES and DE.

Contribution

It presents a novel reinforcement learning-based approach for parameter adaptation in metaheuristics, applicable to CMA-ES and DE, with policies trained on diverse benchmark functions.

Findings

RL-based policies outperform traditional adaptation methods in many cases

Global policies perform comparably to per-function policies

The framework is effective across different problem dimensionalities

Abstract

Parameter adaptation, that is the capability to automatically adjust an algorithm's hyperparameters depending on the problem being faced, is one of the main trends in evolutionary computation applied to numerical optimization. While several handcrafted adaptation policies have been proposed over the years to address this problem, only few attempts have been done so far at applying machine learning to learn such policies. Here, we introduce a general-purpose framework for performing parameter adaptation in continuous-domain metaheuristics based on state-of-the-art reinforcement learning algorithms. We demonstrate the applicability of this framework on two algorithms, namely Covariance Matrix Adaptation Evolution Strategies (CMA-ES) and Differential Evolution (DE), for which we learn, respectively, adaptation policies for the step-size (for CMA-ES), and the scale factor and crossover rate (for DE). We train these policies on a set of 46 benchmark functions at different dimensionalities, with various inputs to the policies, in two settings: one policy per function, and one global policy for all functions. Compared, respectively, to the Cumulative Step-size Adaptation (CSA) policy and to two well-known adaptive DE variants (iDE and jDE), our policies are able to produce competitive results in the majority of cases, especially in the case of DE.