hoonji / udacity_tennis

Project 3: Collaboration and Competition

Environment

This project solves 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, 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.

Installation

1. 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.

2. Clone https://github.com/hoonji/udacity_tennis , place the environment file the directory, and unzip (or decompress) the file.

3. Note that the project contains old dependencies and uses an old python version. The simplest way to set this up is to use conda and install dependencies from the udacity/Value-based-methods repo.

conda create --name drlnd python=3.6
source activate drlnd
git clone https://github.com/udacity/Value-based-methods.git
cd Value-based-methods/python
pip install .

4. Create an IPython kernel for the drlnd conda environment

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

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

Instructions

Run Tennis.ipynb to train the agent, plot tensorboard metrics including the learning curve, and run the agents using the final model.