Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search

TL;DR

This paper introduces a novel approach called Deep Heuristic Search (DHS), which models metaheuristic search as a memory-driven process that enhances the ability to traverse temporal trajectories without relying on probabilistic transition models.

Abstract

Metaheuristic search methods have proven to be essential tools for tackling complex optimization challenges, but their full potential is often constrained by conventional algorithmic frameworks. In this paper, we introduce a novel approach called Deep Heuristic Search (DHS), which models metaheuristic search as a memory-driven process. DHS employs multiple search layers and memory-based exploration-exploitation mechanisms to navigate large, dynamic search spaces. By utilizing model-free memory representations, DHS enhances the ability to traverse temporal trajectories without relying on probabilistic transition models. The proposed method demonstrates significant improvements in search efficiency and performance across a range of heuristic optimization problems.

Figures (6)

• Figure 1: The main components of DHS.
• Figure 2: Examples of different memory depth structures in the DHS framework using an elite memory. The size of deep and shallow memories are $N_d = 10$ and $N_s = 5$, respectively.
• Figure 3: Operation modes for a crossover operator.
• Figure 4: Operation modes for a mutation operator.
• Figure 5: Operation modes for constructing neighborhood zones.