Solving the Pod Repositioning Problem with Deep Reinforced Adaptive Large Neighborhood Search

TL;DR

This paper introduces a novel approach combining Deep Reinforcement Learning with Adaptive Large Neighborhood Search to effectively solve the Pod Repositioning Problem in robotic warehouse systems, outperforming traditional methods.

Contribution

It presents a new hybrid method that uses DRL to dynamically guide ALNS, improving solution quality for the PRP in robotic fulfillment centers.

Findings

DRL-guided ALNS outperforms traditional heuristics and optimization methods.

The approach adapts destroy and repair operators based on learned policies.

Results show significant improvements in solution quality and efficiency.

Abstract

The Pod Repositioning Problem (PRP) in Robotic Mobile Fulfillment Systems (RMFS) involves selecting optimal storage locations for pods returning from pick stations. This work presents an improved solution method that integrates Adaptive Large Neighborhood Search (ALNS) with Deep Reinforcement Learning (DRL). A DRL agent dynamically selects destroy and repair operators and adjusts key parameters such as destruction degree and acceptance thresholds during the search. Specialized heuristics for both operators are designed to reflect PRP-specific characteristics, including pod usage frequency and movement costs. Computational results show that this DRL-guided ALNS outperforms traditional approaches such as cheapest-place, fixed-place, binary integer programming, and static heuristics. The method demonstrates strong solution quality and illustrating the benefit of learning-driven control within combinatorial optimization for warehouse systems.