论文标题
通过智能信息聚合可扩展的多代理强化学习
Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation
论文作者
论文摘要
当观测值仅限于每个代理的当地社区时，我们考虑多代理导航和避免碰撞的问题。我们提出了Insporarl，这是一种用于多机构增强学习（MARL）的新型架构，该架构以分散的方式使用本地信息智能地计算所有代理的路径。具体而言，Indormarl汇总了有关演员和评论家的当地代理社区的信息，并可以使用图形神经网络与任何标准的MARL算法一起使用。我们表明，（1）在培训中，Indormarl的样本效率和性能比基线方法更好，尽管使用了较少的信息，并且（2）在测试中，它可以很好地扩展到具有任意数量的代理和障碍的环境。我们使用四个任务环境说明了这些结果，其中包括一个针对每个代理的预定目标，而代理商共同试图涵盖所有目标。可在https://github.com/nsidn98/informarl上找到代码。
We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which uses local information intelligently to compute paths for all the agents in a decentralized manner. Specifically, InforMARL aggregates information about the local neighborhood of agents for both the actor and the critic using a graph neural network and can be used in conjunction with any standard MARL algorithm. We show that (1) in training, InforMARL has better sample efficiency and performance than baseline approaches, despite using less information, and (2) in testing, it scales well to environments with arbitrary numbers of agents and obstacles. We illustrate these results using four task environments, including one with predetermined goals for each agent, and one in which the agents collectively try to cover all goals. Code available at https://github.com/nsidn98/InforMARL.
