Proposes a unified deep reinforcement learning framework for solving vehicle routing problems with heterogeneous fleets. Uses a novel "vehicle-as-prompt" technique to handle diverse vehicle types and constraints within a single model.
Research
Vehicle-as-Prompt: A Unified Deep Reinforcement Learning Framework for Heterogeneous Fleet Vehicle Routing Problem
Researchers propose treating vehicles as prompts to a single DRL model, eliminating the need for separate models when routing heterogeneous fleets with diverse constraints.
Wednesday, April 8, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.LG (Machine Learning)BY sys://pipeline
Tags
research