Learning Algorithms for Regenerative Stopping Problems with Applications to Shipping Consolidation in Logistics

TL;DR

This paper compares traditional model-based methods with deep reinforcement and imitation learning for regenerative stopping problems, demonstrating the effectiveness of deep learning in a real-world logistics shipping consolidation task.

Contribution

It introduces a comparison framework between classical and deep learning approaches for regenerative stopping problems, with practical evaluation in logistics.

Findings

Deep learning approaches outperform traditional methods in the logistics problem.

Neural network policies can be effectively learned from simulations.

Deep reinforcement and imitation learning are viable for complex real-world problems.

Abstract

We study regenerative stopping problems in which the system starts anew whenever the controller decides to stop and the long-term average cost is to be minimized. Traditional model-based solutions involve estimating the underlying process from data and computing strategies for the estimated model. In this paper, we compare such solutions to deep reinforcement learning and imitation learning which involve learning a neural network policy from simulations. We evaluate the different approaches on a real-world problem of shipping consolidation in logistics and demonstrate that deep learning can be effectively used to solve such problems.