GLDQN: Explicitly Parameterized Quantile Reinforcement Learning for Waste Reduction

We study the problem of restocking a grocery store's inventory with perishable items over time, from a distributional point of view. The objective is to maximize sales while minimizing waste, with uncertainty about the actual consumption by costumers. This problem is of a high relevance today, given the growing demand for food and the impact of food waste on the environment, the economy, and purchasing power. We frame inventory restocking as a new reinforcement learning task that exhibits stochastic behavior conditioned on the agent's actions, making the environment partially observable. We introduce a new reinforcement learning environment based on real grocery store data and expert knowledge. This environment is highly stochastic, and presents a unique challenge for reinforcement learning practitioners. We show that uncertainty about the future behavior of the environment is not handled well by classical supply chain algorithms, and that distributional approaches are a good way to account for the uncertainty. We also present GLDQN, a new distributional reinforcement learning algorithm that learns a generalized lambda distribution over the reward space. We show that GLDQN outperforms other distributional reinforcement learning approaches in our partially observable environments, in both overall reward and generated waste.