Detect and Act: Automated Dynamic Optimizer through Meta-Black-Box Optimization

TL;DR

This paper introduces a reinforcement learning-assisted method for automated detection and adaptation in evolutionary algorithms to effectively solve dynamic optimization problems, outperforming existing approaches.

Contribution

It presents a novel deep Q-network based framework for automatic environment variation detection and self-adaptation in evolutionary algorithms, reducing reliance on human-crafted strategies.

Findings

Demonstrates superior performance over state-of-the-art methods on diverse DOPs.

Shows effective generalization to unseen dynamic environments.

Provides a comprehensive DOPs testbed for validation.

Abstract

Dynamic Optimization Problems (DOPs) are challenging to address due to their complex nature, i.e., dynamic environment variation. Evolutionary Computation methods are generally advantaged in solving DOPs since they resemble dynamic biological evolution. However, existing evolutionary dynamic optimization methods rely heavily on human-crafted adaptive strategy to detect environment variation in DOPs, and then adapt the searching strategy accordingly. These hand-crafted strategies may perform ineffectively at out-of-box scenarios. In this paper, we propose a reinforcement learning-assisted approach to enable automated variation detection and self-adaption in evolutionary algorithms. This is achieved by borrowing the bi-level learning-to-optimize idea from recent Meta-Black-Box Optimization works. We use a deep Q-network as optimization dynamics detector and searching strategy adapter: It is fed as input with current-step optimization state and then dictates desired control parameters to underlying evolutionary algorithms for next-step optimization. The learning objective is to maximize the expected performance gain across a problem distribution. Once trained, our approach could generalize toward unseen DOPs with automated environment variation detection and self-adaption. To facilitate comprehensive validation, we further construct an easy-to-difficult DOPs testbed with diverse synthetic instances. Extensive benchmark results demonstrate flexible searching behavior and superior performance of our approach in solving DOPs, compared to state-of-the-art baselines.