This repository contains my solution for Udacity's Deep RL Nanodegree's Continuous Control project.

This project works with 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 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. This version contains 20 identical agents, each with its own copy of the environment.

The baseline is to make sure that agents 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.

• Clone the project for running in your local environment.
• Install the required Python dependencies as mentioned in the Udacity DeepRL Nanodegree.

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

   • Version 1: One (1) Agent

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

   • 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.

   (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. Place the file inside the continuous-control repository, e.g. in Linux your project directory will look like this:

   • Reacher_Linux/
   • src
   • weights
   • ...

• Execute from the command line after following the steps in the "Getting Started" section.

  • Go to the base directory: cd continuous-control
  • Run python -m src.train --path <PATH TO UNITY ENV>, for e.g. python -m src.train --path Reacher_Linux_NoVis/Reacher.x86_64
  • Optionally you can include --print_every argument to adjust verbosity

• The trained weights by default will be saved in weights/ directory.

• For the full report and explanation of the algorithm, checkout Report.pdf.