links: Medium article on improved stability

This project is solving the Tennis environment.

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 8 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.

The task is episodic, and in order to solve the environment, your agents must get an average score of +0.5 (over 100 consecutive episodes, after taking the maximum over both agents). Specifically,

• After each episode, the rewards that each agent received (without discounting) is added, to get a score for each agent. This yields 2 (potentially different) scores. We then take the maximum of these 2 scores.
• This yields a single score for each episode.

The environment is considered solved, when the average (over 100 episodes) of those scores is at least +0.5.

1. With DDPG agent (single -agent RL) The environment was solved in 3036 episodes. Average running scores graph is below

2. Extended training If the training is continued after solving the environment (i.e avg score > .5) we see that agent is continously improving reaching to avg score >3 in another 765 episodes. In this training i have reduced the noise.

3. With maddpg agent (multi-agent reinforcement training.) The environment was solved in 900 episodes.

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 3.6.

   • Linux or Mac:

   conda create --name game python=3.6
   source activate game

   • Windows:

   conda create --name game python=3.6 
   activate game

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

   • Next, install the classic control environment group by following the instructions here.
   • Then, install the box2d environment group by following the instructions here.

3. Clone the repository (if you haven't already!), and navigate to the python/ folder. Then, install several dependencies.

git clone https://github.com/abhismatrix1/Tennis-MultiAgent.git
cd Tennis-MultiAgent/python
pip install .

4. Download the environment from one of the links below. You need only select the environment that matches your operating system:

   • Linux: click here
   • Mac OSX: click here
   • Windows (32-bit): click here
   • Windows (64-bit): click here

   (For Windows users) Check out this link if you need help with determining if your computer is running a 32-bit version or 64-bit version of the Windows operating system.

   (For AWS) If you'd like to train the agent on AWS (and have not enabled a virtual screen), then please use this link to obtain the "headless" version of the environment. You will not be able to watch the agent without enabling a virtual screen, but you will be able to train the agent. (To watch the agent, you should follow the instructions to enable a virtual screen, and then download the environment for the Linux operating system above.)

5. Place the file in the this GitHub repository, in the Tennis-MultiAgent/ folder, and unzip (or decompress) the file.

Follow the instructions in Tennis..ipynb to get started with training your own agent!