What does this research mean for the field?

The Evo-RL framework, which synergizes Deep Reinforcement Learning and Genetic Algorithms, significantly outperforms state-of-the-art heuristics and deep RL baselines in solving dynamic pickup and delivery problems with strict constraints like LIFO and time windows. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to improve solutions for complex dynamic pickup and delivery problems using Evo-RL, which combines reinforcement learning and genetic algorithms.

May 9, 2026Transportation Research Part E Logistics and Transportation Review0 citationsOpen Access

View Full Paper

A collaborative evolutionary reinforcement learning approach to dynamic pickup and delivery challenges

XYXiaoying Yang YLYiran Li TCTianxiang Cui

Key Points

This research aims to improve solutions for complex dynamic pickup and delivery problems using Evo-RL, which combines reinforcement learning and genetic algorithms.
Developed Evo-RL framework for strategic planning and optimization in delivery tasks.
Evaluated the approach against large-scale DPDP benchmarks from the ICAPS 2021 competition.
Addressed stochastic delivery challenges with strict LIFO and time window constraints.
Evo-RL significantly outperforms heuristics, achieving higher solution quality and faster convergence.
Demonstrates robust policy learning capabilities despite reward sparsity and complex constraints.

Abstract

• Evo-RL synergizes Deep RL and GA for dynamic pickup and delivery problems. • RL handles strategic allocation while GA refines routes to mitigate reward sparsity. • Effectively handles strict LIFO and time window constraints in side-loading fleets. • Models stochastic delivery times and distances to guide robust policy learning. • Significantly outperforms heuristics and RL baselines on large-scale benchmarks. In the contemporary landscape of global logistics, the efficient delivery of commodities at scale has become imperative. Central to this challenge is the Dynamic Pickup and Delivery Problem (DPDP). While DPDP is inherently complex due to stochastic orders and real-time requirements, it becomes particularly formidable in specific supply chain variants constrained by strict loading protocols, such as the Last-In-First-Out (LIFO) requirement found in air cargo and side-loading fleets. Traditional heuristics often struggle to escape local optima under such rigid constraints, while standard Reinforcement Learning (RL) faces difficulties with reward sparsity and high-dimensional action spaces. To address these challenges, we propose Evo-RL, a holistic evolutionary reinforcement learning framework. Unlike disjointed hybrid methods, Evo-RL establishes a synergistic closed loop: the RL agent acts as a strategic planner to capture latent spatiotemporal dependencies and generate feasible initial assignments, while a population-based Genetic Algorithm (GA) serves as an optimization engine to refine sequences and provide dense feedback signals. This collaborative mechanism allows the RL agent to overcome reward sparsity by learning from the diverse evolutionary population. We evaluate our approach on the real-world, large-scale DPDP benchmark from the ICAPS 2021 competition. Empirical results demonstrate that Evo-RL significantly outperforms state-of-the-art heuristics and deep RL baselines in terms of solution quality and convergence speed, proving its efficacy in handling dynamic constraints and large-scale complexities.

Perguntar à IA

Bookmark

View Full Paper

Cite This Study

Yang et al. (Thu,) studied this question.

synapsesocial.com/papers/69fed19ab9154b0b82878ee3 https://doi.org/https://doi.org/10.1016/j.tre.2026.104885

Perguntar à IA

Bookmark

View Full Paper