D-QMIX: Multi-Step Sequential Forward Dynamics Modeling with Global State and Self-Attention for Sample-Efficient Multi-Agent Reinforcement Learning

This repository contains the implementation of D-QMIX on both SMAC and MPE environments.

File Description

├── SMAC                                         # Code for training D-QMIX on SMAC environments
│  
├── MPE                                          # Code for training D-QMIX on MPE environments