Middle-mile logistics through the lens of goal-conditioned reinforcement learning

Abstract

Middle-mile logistics describes the problem of routing parcels through a network of hubs linked by trucks with finite capacity. We rephrase this as a multi-object goal-conditioned MDP. Our method combines graph neural networks with model-free RL, extracting small feature graphs from the environment state.

Published at Neural Information Processing Systems (NeurIPS) 2023 Workshop on Goal-Conditioned Reinforcement Learning