This repository contains material from the third Udacity DRL procjet and the coding exercice DDPG-pendulum.

In this project, we train a MADDPG multi-agent to solve two types of environment.

First Tennis :

In this environment, two agents control rackets to bounce a ball over a net. If an agent hits the ball over the net, it receives a reward of $+0.1$. If an agent lets a ball hit the ground or hits the ball out of bounds, it receives a reward of $-0.01$. Thus, the goal of each agent is to keep the ball in play.

The observation space consists of $24$ variables corresponding to the position and velocity of the ball and racket. Each agent receives its own, local observation. Two continuous actions are available, corresponding to movement toward (or away from) the net, and jumping.

Second, Soccer :

In this discrete control environment, four agents compete in a $2$ strikers vs $2$ goalies in soccer game. The goal for a Striker is to get the ball into the opponent's goal and for Goalie is to keep the ball out of the goal. A striker/goalie receive a reward of $\pm 1$ when ball enters goal and $\mp 10^{-3}$ for existential.

An environment is considered solved, when an average score of +0.5 over 100 consecutive episodes, and for each agent is obtained.

To set up your python environment to run the code in this repository, follow the instructions below.

1. Create (and activate) a new environment with Python 3.9.

   • Linux or Mac:

   conda create --name drlnd 
   source activate drlnd

   • Windows:

   conda create --name drlnd 
   activate drlnd

2. Follow the instructions in Pytorch web page to install pytorch and its dependencies (PIL, numpy,...). For Windows and cuda 11.6

   conda install pytorch torchvision torchaudio cudatoolkit=11.6 -c pytorch -c conda-forge

3. Follow the instructions in this repository to perform a minimal install of OpenAI gym.

   • Install the box2d environment group by following the instructions here.

   pip install gym[box2d]

4. Follow the instructions in third Udacity DRL procjet to get the environment.

5. Clone the repository, and navigate to the python/ folder. Then, install several dependencies.

git clone https://github.com/eljandoubi/MADDPG-for-Collaboration-and-Competition.git
cd MADDPG-for-Collaboration-and-Competition/python
pip install .

6. Create an IPython kernel for the drlnd environment.

python -m ipykernel install --user --name drlnd --display-name "drlnd"

7. Before running code in a notebook, change the kernel to match the drlnd environment by using the drop-down Kernel menu.

You can train and/or inference Tennis environment:

Run the training and/or inference cell of Tennis.ipynb.

The pre-trained models with the highest score are stored in Tennis_checkpoint.

Same for Soccer but the current checkpoint isn't the best.

The implementation and resultats are discussed in the report.