In this project I share my solution for the Udacity Deep Reinforcement Learning Project 3 - Continuous Control 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, we add up the rewards that each agent received (without discounting), 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.
We used the method of Multi Agent Deep Deterministic Policy Gradient (MADDPG) to solve this project.
In this project each agent player has its own actor and critic network, but both are sharing the same random replay buffer.
Sharing the same replay buffer, increase the speed of learning as it collects a massive amount of experinces really quicly.
To set up your python environment to run the code in this repository, follow the instructions below.
-
Create (and activate) a new environment with Python 3.6.
- Linux or Mac:
conda create --name drlnd python=3.6 source activate drlnd
- Windows:
conda create --name drlnd python=3.6 activate drlnd
-
Clone the Udacity Deep Reinforcment Learning repository (if you haven't already!), and navigate to the
python/
folder. Then, install several dependencies.
git clone https://github.com/udacity/deep-reinforcement-learning.git
cd deep-reinforcement-learning/python
pip install .
- Create an IPython kernel for the
drlnd
environment.
python -m ipykernel install --user --name drlnd --display-name "drlnd"
-
Clone this repository and open a new notebook and open the file
Tennis-MADDPG.ipynb
-
Before running code in a notebook, change the kernel to match the
drlnd
environment by using the drop-downKernel
menu. -
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
-
Place the file in the DRLND GitHub repository, in the
DRLND-3-Multi-Agent/
folder, and unzip (or decompress) the file.
Follow the instructions in Tennis-MADDPG.ipynb
to run the agent training or to load and run the agent using the pretrained model!