FloW

该数据集是一个自动驾驶车辆模拟模型，涵盖了在不同高速公路网络上行驶的情景，这些车辆可以被强化学习算法或人类行为模型所控制。同时，该数据集采用了智能驾驶员模型（IDM）来模拟类似人类的驾驶行为。规模上涵盖了多辆车辆和多个高速公路。任务的设定是在奖励函数不精确情况下的强化学习。

This dataset is an autonomous vehicle simulation model covering driving scenarios across various highway networks. Vehicles in the scenarios can be controlled by either reinforcement learning algorithms or human behavior models. The Intelligent Driver Model (IDM) is adopted to simulate human-like driving behaviors. The dataset scales to include multiple vehicles and multiple highways, with the task tailored for reinforcement learning under imprecise reward functions.