Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems
This work addresses the problem of finding better solutions for vehicle routing problems, which is relevant for logistics and transportation industries.
This paper introduces a Multi-Decoder Attention Model (MDAM) that trains multiple diverse policies to solve vehicle routing problems, outperforming state-of-the-art deep learning models. It also incorporates an Embedding Glimpse layer to enhance policy quality.
We present a novel deep reinforcement learning method to learn construction heuristics for vehicle routing problems. In specific, we propose a Multi-Decoder Attention Model (MDAM) to train multiple diverse policies, which effectively increases the chance of finding good solutions compared with existing methods that train only one policy. A customized beam search strategy is designed to fully exploit the diversity of MDAM. In addition, we propose an Embedding Glimpse layer in MDAM based on the recursive nature of construction, which can improve the quality of each policy by providing more informative embeddings. Extensive experiments on six different routing problems show that our method significantly outperforms the state-of-the-art deep learning based models.