Udacity Deep Reinforcement Learning Nanodegree Project: Continuous Control

Introduction

The goal for this project is solving the Reacher environment.

In this environment, 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 the 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.

Distributed Training

The second version (the one used in this project) of the environment contains 20 identical agents, each with its own copy of the environment.

Solving the Environment

For solving the environment the 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).

The environment is considered solved, when the average (over 100 episodes) of those average scores is at least +30.

Getting Started

1. Clone this repository and install the dependencies specified in the official DRLND-repository

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

   • Version 2: Twenty (20) Agents
     • 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.

3. Place the file in this GitHub repository and unzip (or decompress) the file. Then rename the folder to Reacher. (Now Reacher/Reacher.exe should exist.)

Instructions

Simply execute the cells in training.ipynb to get started with training the agent or simply execute demonstration.ipynb for a demonstration of the trained agent.