This project trains an agent to solve the Unity "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.
Directions for installing dependencies can be found at: https://github.com/udacity/deep-reinforcement-learning#dependencies
You'll also need to clone the above project, change into the python directory, and install the dependencies:
pip install -e .
- Download the environment:
For this project, you will not need to install Unity - this is because we have already built the environment for you, and you can download it 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 Then, place the file in the p3_collab-compet/ folder in the DRLND GitHub repository, and unzip (or decompress) the file.
To train the agent, you should run main.py. For example:
pythonw main.py --episodes 5000 --saveto checkpoint.pth --saveplot scores.png --environnment path/to/Tennis.app
To run in eval mode:
pythonw main.py --eval=True --loadfrom checkpoint.pth --episodes 10