论文标题
具有二阶动力学的车辆的有效域覆盖范围通过多代理增强学习
Efficient Domain Coverage for Vehicles with Second-Order Dynamics via Multi-Agent Reinforcement Learning
论文作者
论文摘要
涵盖指定区域的协作自主多机构系统具有许多潜在的应用，例如搜索和救援，森林消防和实时高分辨率监控。此类覆盖问题的传统方法涉及基于传感器数据设计基于模型的控制策略。但是，设计基于模型的控制器具有挑战性，而最先进的经典控制策略仍然表现出很大程度的次级临时性。在本文中，我们为涉及具有二阶动力的代理的多代理有效域覆盖问题提出了增强学习（RL）方法。我们的方法基于多代理近端策略优化算法（MAPPO）。我们提出的网络体系结构包括LSTM和自我注意力的结合，这使训练有素的政策能够适应可变数量的代理。我们训练有素的政策大大优于最先进的古典控制政策。我们在各种模拟实验中演示了我们提出的方法。
Collaborative autonomous multi-agent systems covering a specified area have many potential applications, such as UAV search and rescue, forest fire fighting, and real-time high-resolution monitoring. Traditional approaches for such coverage problems involve designing a model-based control policy based on sensor data. However, designing model-based controllers is challenging, and the state-of-the-art classical control policy still exhibits a large degree of sub-optimality. In this paper, we present a reinforcement learning (RL) approach for the multi-agent efficient domain coverage problem involving agents with second-order dynamics. Our approach is based on the Multi-Agent Proximal Policy Optimization Algorithm (MAPPO). Our proposed network architecture includes the incorporation of LSTM and self-attention, which allows the trained policy to adapt to a variable number of agents. Our trained policy significantly outperforms the state-of-the-art classical control policy. We demonstrate our proposed method in a variety of simulated experiments.
