Generalization in Deep RL for TSP Problems via Equivariance and Local Search

TL;DR

This paper introduces a deep RL approach for TSP that emphasizes generalization to larger instances by leveraging equivariance and local search, validated through empirical evaluation and ablation studies.

Contribution

A novel deep RL method for TSP that improves generalization to larger instances using equivariance and local search techniques.

Findings

Outperforms existing deep RL methods on TSP benchmarks

Equivariance and local search significantly enhance generalization

Ablation study confirms the contribution of each component

Abstract

Deep reinforcement learning (RL) has proved to be a competitive heuristic for solving small-sized instances of traveling salesman problems (TSP), but its performance on larger-sized instances is insufficient. Since training on large instances is impractical, we design a novel deep RL approach with a focus on generalizability. Our proposition consisting of a simple deep learning architecture that learns with novel RL training techniques, exploits two main ideas. First, we exploit equivariance to facilitate training. Second, we interleave efficient local search heuristics with the usual RL training to smooth the value landscape. In order to validate the whole approach, we empirically evaluate our proposition on random and realistic TSP problems against relevant state-of-the-art deep RL methods. Moreover, we present an ablation study to understand the contribution of each of its component