Model-based controlled learning of MDP policies with an application to lost-sales inventory control

Recent literature established that neural networks can represent good MDP policies across a range of stochastic dynamic models in supply chain and logistics. To overcome limitations of the model-free algorithms typically employed to learn/find such neural network policies, a model-based algorithm is proposed that incorporates variance reduction techniques. For the classical lost sales inventory model, the algorithm learns neural network policies that are superior to those learned using model-free algorithms, while also outperforming heuristic benchmarks. The algorithm may be an interesting candidate to apply to other stochastic dynamic problems in supply chain and logistics.