We present a new practical framework based on deep reinforcement learning and decision-time planning for real-world vehicle repositioning on ride-hailing (a type of mobility-on-demand, MoD) platforms. Our approach learns the spatiotemporal state-value function using a batch training algorithm with deep value networks. The optimal repositioning action is generated on-demand through value-based policy search, which combines planning and bootstrapping with the value networks. For the large-fleet problems, we develop several algorithmic features that we incorporate into our framework and that we demonstrate to induce coordination among the algorithmically-guided vehicles. We benchmark our algorithm with baselines in a ride-hailing simulation environment to demonstrate its superiority in improving income efficiency measured by income-per-hour. We have also designed and run a real-world experiment program with regular drivers on a major ride-hailing platform. We have observed significantly positive results on key metrics comparing our method with experienced drivers who performed idle-time repositioning based on their own expertise.

我们提出了一个基于深度强化学习和决策时间规划的新实用框架，用于在叫车（一种按需移动，MoD）平台上重新定位现实世界的车辆。我们的方法使用具有深度值网络的批量训练算法来学习时空状态值函数。最优重新定位动作是通过基于价值的策略搜索按需生成的，它将规划和引导与价值网络相结合。对于大型车队问题，我们开发了几个算法特征，我们将这些特征合并到我们的框架中，并且我们证明了这些特征可以在算法引导的车辆之间进行协调。我们在乘车模拟环境中使用基线对我们的算法进行基准测试，以证明其在提高以每小时收入衡量的收入效率方面的优势。我们还在一个主要的叫车平台上设计并运行了一个真实世界的实验程序，其中有普通司机。将我们的方法与根据自己的专业知识执行空闲时间重新定位的经验丰富的驾驶员进行比较，我们在关键指标上观察到了显着的积极结果。