Multi-Agent Reinforcement Learning System Using Multi-Agent Proximal Policy Optimizer Algorithm in SMAC Environment

Multi-Agent Reinforcement Learning (MARL) is a sub-field of reinforcement learning that focuses on studying the behavior of multiple learning agents that coexist in a shared environment. In this paper, we will examine a war scenario within StartCraft II Multi-Agent Challenges (SMAC) environment to implement a multi-agent system. For training, one of the well-known MARL algorithms was used, namely Multi-Agent Proximal Policy Optimization (MAPPO). This algorithm works on navigating the agents to cooperate with each other to achieve the desired goals. We will then use two offered metrics: battle won mean and dead allies mean in the SMAC environment to evaluate the performance of the MAPPO algorithm. The result showed that the MAPPO algorithm reached the greatest value of battle won mean with one million iterations and reached the lowest value of dead allies mean metrics with less than one million iterations. The hardware that we use in this work is CPU Cor i7 11800H, with 32 GB Ram and RTX 3080 laptop GPU, with CUDA Toolkit 11.7.1, and Pytorch 1.7.1.