This repository provides centralized implementations of state-of-the-art multi-agent RL algorithms including IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet. The algorithms are trained and evaluated on SMAC, the decentralized micromanagement scenario in StarCraft II, which serves as a standard benchmark for cooperative multi-agent learning. It supports both value-decomposition methods and policy gradient approaches for cooperative multi-agent settings.