Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping
This addresses the efficiency of package sorting in warehouses, but it is incremental as it builds on existing multi-agent reinforcement learning and distributionally robust optimization methods.
The paper tackled the problem of uncertain and dynamic package induction rates in Amazon robotic warehouses, which cause increased package recirculation, by introducing a Distributionally Robust Multi-Agent Reinforcement Learning framework that reduced package recirculation by an average of 80% in simulations.
In Amazon robotic warehouses, the destination-to-chute mapping problem is crucial for efficient package sorting. Often, however, this problem is complicated by uncertain and dynamic package induction rates, which can lead to increased package recirculation. To tackle this challenge, we introduce a Distributionally Robust Multi-Agent Reinforcement Learning (DRMARL) framework that learns a destination-to-chute mapping policy that is resilient to adversarial variations in induction rates. Specifically, DRMARL relies on group distributionally robust optimization (DRO) to learn a policy that performs well not only on average but also on each individual subpopulation of induction rates within the group that capture, for example, different seasonality or operation modes of the system. This approach is then combined with a novel contextual bandit-based predictor of the worst-case induction distribution for each state-action pair, significantly reducing the cost of exploration and thereby increasing the learning efficiency and scalability of our framework. Extensive simulations demonstrate that DRMARL achieves robust chute mapping in the presence of varying induction distributions, reducing package recirculation by an average of 80\% in the simulation scenario.