Multi-Agent Reinforcement Learning for Visibility-based Persistent Monitoring

1 code implementation • 2 Nov 2020 • Jingxi Chen, Amrish Baskaran, Zhongshun Zhang, Pratap Tokekar

Specifically, we present a Multi-Agent Graph Attention Proximal Policy Optimization (MA-G-PPO) algorithm that takes as input the local observations of all agents combined with a low resolution global map to learn a policy for each agent.

Graph Attention Multi-agent Reinforcement Learning +2