/pytorch-maddpg

A pytorch implementation of MADDPG (multi-agent deep deterministic policy gradient)

Primary LanguagePython

An implementation of MADDPG

1. Introduction

This is a pytorch implementation of multi-agent deep deterministic policy gradient algorithm.

The experimental environment is a modified version of Waterworld based on MADRL.

2. Environment

The main features (different from MADRL) of the modified Waterworld environment are:

  • evaders and poisons now bounce at the wall obeying physical rules
  • sizes of the evaders, pursuers and poisons are now the same so that random actions will lead to average rewards around 0.
  • need exactly n_coop agents to catch food.

3. Dependency

  • pytorch
  • visdom
  • python==3.6.1 (recommend using the anaconda/miniconda)
  • if you need to render the environments, opencv is required

4. Install

  • Install MADRL.
  • Replace the madrl_environments/pursuit directory with the one in this repo.
  • python main.py

if scene rendering is enabled, recommend to install opencv through conda-forge.

5. Results

two agents, cooperation = 2

The two agents need to cooperate to achieve the food for reward 10.

PNG/demo.gif

PNG/3.png

the average

PNG/4.png

one agent, cooperation = 1

PNG/newplot.png

6. TODO

  • reproduce the experiments in the paper with competitive environments.