DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization

TL;DR

DeepACO introduces a neural-enhanced framework that automates heuristic design in Ant Colony Optimization, improving performance across multiple combinatorial problems without manual tuning.

Contribution

It presents a novel deep reinforcement learning-based approach to enhance and automate heuristics in ACO, reducing manual effort and improving generalization.

Findings

Outperforms traditional ACO on eight combinatorial problems.

Matches or exceeds problem-specific methods on routing problems.

Uses a single neural architecture and hyperparameters across tasks.

Abstract

Ant Colony Optimization (ACO) is a meta-heuristic algorithm that has been successfully applied to various Combinatorial Optimization Problems (COPs). Traditionally, customizing ACO for a specific problem requires the expert design of knowledge-driven heuristics. In this paper, we propose DeepACO, a generic framework that leverages deep reinforcement learning to automate heuristic designs. DeepACO serves to strengthen the heuristic measures of existing ACO algorithms and dispense with laborious manual design in future ACO applications. As a neural-enhanced meta-heuristic, DeepACO consistently outperforms its ACO counterparts on eight COPs using a single neural architecture and a single set of hyperparameters. As a Neural Combinatorial Optimization method, DeepACO performs better than or on par with problem-specific methods on canonical routing problems. Our code is publicly available at https://github.com/henry-yeh/DeepACO.