Continuous Control

Table of Contents

1. Installation
2. Project Motivation
3. Project Overview
4. Getting Started
5. Instructions
6. Licensing, Authors, and Acknowledgements

Installation

Apart from Anaconda distribution of Python, this code should requires UnityML.

Project Motivation

In this project, I have applied DDPG with Experience Replay to help a double-jointed arm can move to target locations.

Project Overview

For this project, a double-jointed arm can move to target locations. A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of your agent is to maintain its position at the target location for as many time steps as possible.

The observation space consists of 33 variables corresponding to position, rotation, velocity, and angular velocities of the arm. Each action is a vector with four numbers, corresponding to torque applicable to two joints. Every entry in the action vector should be a number between -1 and 1.

To solve the environment we have two options:

Option 1: Solve the First Version

The task is episodic, and in order to solve the environment, your agent must get an average score of +30 over 100 consecutive episodes.

Option 2: Solve the Second Version

The barrier for solving the second version of the environment is slightly different, to take into account the presence of many agents. In particular, your agents must get an average score of +30 (over 100 consecutive episodes, and over all 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 20 (potentially different) scores. We then take the average of these 20 scores. This yields an average score for each episode (where the average is over all 20 agents).

Getting Started

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

   • Version 1:
   • Linux: click here
   • Mac OSX: click here
   • Windows (32-bit): click here
   • Windows (64-bit): click here

   -Version 2:

   • 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 (version 1) or this link (version 2) 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. Please follow the instructions in the DRLND GitHub repository to setup the Python Environment.

Instructions

1. Check the instructions in Continuous_Control.ipynb

Licensing, Authors, and Acknowledgements

• Udacity (for providing the starter code.)