Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning

TL;DR

This paper introduces a novel neural network with heterogeneous attention for deep reinforcement learning to effectively solve the pickup and delivery problem, addressing pairing and precedence constraints.

Contribution

It proposes a new attention mechanism tailored for PDP, improving solution quality and generalization over existing methods.

Findings

Outperforms state-of-the-art heuristics and deep learning models

Handles pairing and precedence constraints effectively

Generalizes well to various distributions and sizes

Abstract

Recently, there is an emerging trend to apply deep reinforcement learning to solve the vehicle routing problem (VRP), where a learnt policy governs the selection of next node for visiting. However, existing methods could not handle well the pairing and precedence relationships in the pickup and delivery problem (PDP), which is a representative variant of VRP. To address this challenging issue, we leverage a novel neural network integrated with a heterogeneous attention mechanism to empower the policy in deep reinforcement learning to automatically select the nodes. In particular, the heterogeneous attention mechanism specifically prescribes attentions for each role of the nodes while taking into account the precedence constraint, i.e., the pickup node must precede the pairing delivery node. Further integrated with a masking scheme, the learnt policy is expected to find higher-quality solutions for solving PDP. Extensive experimental results show that our method outperforms the state-of-the-art heuristic and deep learning model, respectively, and generalizes well to different distributions and problem sizes.