Multi-parameter Control for the $(1+(\lambda,\lambda))$-GA on OneMax via Deep Reinforcement Learning

TL;DR

This paper explores using deep reinforcement learning to develop multi-parameter control policies for the $(1+(rac{}{})$-GA on OneMax, achieving significant performance improvements over existing policies across various problem sizes.

Contribution

It demonstrates the effectiveness of deep reinforcement learning in controlling multiple parameters simultaneously for evolutionary algorithms, surpassing previous policies on the OneMax benchmark.

Findings

RL-based policies outperform all known control policies.

A simple derived policy improves performance by 27%.

Performance gains are consistent up to problem size 40,000.

Abstract

It is well known that evolutionary algorithms can benefit from dynamic choices of the key parameters that control their behavior, to adjust their search strategy to the different stages of the optimization process. A prominent example where dynamic parameter choices have shown a provable super-constant speed-up is the $(1+(\lambda,\lambda))$ Genetic Algorithm optimizing the OneMax function. While optimal parameter control policies result in linear expected running times, this is not possible with static parameter choices. This result has spurred a lot of interest in parameter control policies. However, many works, in particular theoretical running time analyses, focus on controlling one single parameter. Deriving policies for controlling multiple parameters remains very challenging. In this work we reconsider the problem of the $(1+(\lambda,\lambda))$ Genetic Algorithm optimizing OneMax. We decouple its four main parameters and investigate how well state-of-the-art deep reinforcement learning techniques can approximate good control policies. We show that although making deep reinforcement learning learn effectively is a challenging task, once it works, it is very powerful and is able to find policies that outperform all previously known control policies on the same benchmark. Based on the results found through reinforcement learning, we derive a simple control policy that consistently outperforms the default theory-recommended setting by $27\%$ and the irace-tuned policy, the strongest existing control policy on this benchmark, by $13\%$, for all tested problem sizes up to $40{,}000$.