Demand Acceptance using Reinforcement Learning for Dynamic Vehicle Routing Problem with Emission Quota

TL;DR

This paper proposes a reinforcement learning-based framework for dynamic vehicle routing with emission constraints, enabling demand acceptance decisions and route optimization under uncertainty.

Contribution

It introduces a novel formalization of the DS-QVRP-RR problem and develops hybrid algorithms combining reinforcement learning with combinatorial optimization.

Findings

Effective demand rejection and routing under emission constraints

Outperforms traditional methods in computational experiments

Applicable to various input scenarios with uncertain horizons

Abstract

This paper introduces and formalizes the Dynamic and Stochastic Vehicle Routing Problem with Emission Quota (DS-QVRP-RR), a novel routing problems that integrates dynamic demand acceptance and routing with a global emission constraint. A key contribution is a two-layer optimization framework designed to facilitate anticipatory rejections of demands and generation of new routes. To solve this, we develop hybrid algorithms that combine reinforcement learning with combinatorial optimization techniques. We present a comprehensive computational study that compares our approach against traditional methods. Our findings demonstrate the relevance of our approach for different types of inputs, even when the horizon of the problem is uncertain.