chrispalmernz/drlnd_p3_collab_compet

Udacity Deep Reinforcement Learning Nanodegree Project 3

Udacity Deep Reinforcement Learning Nanodegree - Project 3

Collaboration and Competition

Use two agents to play tennis

Introduction

The movie below is from a Deep Deterministic Policy Gradient (DDPG) Agent I have trained...

 

This movie is from a Twin Delayed DDPG Agent I have trained...*

The project uses 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.

Distributed Training

Getting Started

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.

   (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.)

2. Place the file in the DRLND GitHub repository, in the p3_collab-compet/ folder, and unzip (or decompress) the file.

Instructions

The Jupyter Notebook Tennis.ipynb must be followed to reproduce the training performed. For the Deep Deterministic Policy Gradient (DDPG) model it calls Agent and Model code in the files ddpg_agent.py and model.py. For the Twin Delayed DDPG model it calls equivalent Agent and Model code in td_ddpg_agent.py and td_ddpg_model.py. These must also be located in the working directory.

One thing that needs changing is the tennisenv definition early in the notebook - it must contain the path to wherever you have extracted the Reacher environment, as described in the Getting Started section above.

Report

Please see the report.md for a discussion of the algorith and model, and results of running the experiment.