Flight_maddpg

An implementation of MADDPG

1 Introduction

This is a tensorflow implementation of MADDPG, however, environment is different.

2 Dependency

• tensorflow
• matplotlib
• nunpy
• python==3.6.1 (recommend using the anaconda/miniconda)
• gym
• ILSVR2015 VID
  

3 Train

python train_code.py

4 Result

Three Agent include Competition and cooperation