Reward Shaping

IoT-driven dynamic replenishment of fresh produce in the presence of seasonal variations: A deep reinforcement learning approach using reward shaping
IoT-driven dynamic replenishment of fresh produce in the presence of seasonal variations: A deep reinforcement learning approach using reward shaping

This study, published in Omega, a prominent journal in Management Science, investigates the application of Deep Reinforcement Learning (DRL) to dynamic replenishment in fresh produce supply chain. We specifically address the bidirectional seasonal variations in both supply lead time and demand of fresh produce. To enhance dynamic replenishment performance, a Reward shaping function was innovatively designed based on the "zero-inventory" paradigm.

Feb 12, 2025