Deep Reinforcement Learning Agent to Solve Unity Reacher

This project was done as part of the Udacity Deep Reinforcement Learning Nanodegree. DDPG (Deep Deterministic Policy Gradient) algorithm was used in this project to teach 20 agents simultaneously to move double-jointed arms to target locations in a Unity environment. For this project, I used the Reacher environment.

For viewing a video of a trained agent using this repository click here.

Introduction

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.

Getting Started

1. 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.

   (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 in the GitHub repository, in the folder, and unzip (or decompress) the file.

3. For Installing this code, you will need to install the dependencies.

Dependencies

Pytorch, Numpy, Matplotlib, unityagents, Jupyter Notebook

Solving the Environment

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).

The environment is considered solved, when the average (over 100 episodes) of those average scores is at least +30. The agents trained using the code in this repository managed to solve the environment in 35 episodes!