This project is part of Udacity Deep Reinforcement Learning Nanodegree. This project aims to develop and train a Deep Reinforcement Learning (RL) agent to Unity's 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. 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.

There are two versions of the Unity environment:

• The first version contains a single agent.
• The second version contains 20 identical agents, each with its own copy of the environment.

The second version is useful for algorithms like PPO, A3C, and D4PG that use multiple (non-interacting, parallel) copies of the same agent to distribute the task of gathering experience.

The solution provided in this repository focuses on solving the second versions. In this environment, the agent is considered successful when it gets an average score of 30 (over 100 consecutive episodes, and over all 20 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. Examples of trained agents are shown below.

These instructions will get you a copy of the project up and running on your local machine.

1. Create (and activate) a new environment with Python 3.6.

   • Linux or Mac:

   conda create --name drlnd python=3.6
   source activate drlnd

   • Windows:

   conda create --name drlnd python=3.6 
   activate drlnd

2. Follow the instructions in this repository to perform a minimal install of OpenAI gym.

3. Clone this repository and install several dependencies.

   git clone https://github.com/ragamarkely/deep_rl_continuous_control.git 
   pip install .

4. 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.)

5. Unzip and place the file in the root folder of this repository.

6. Create an IPython kernel for the drlnd environment.

   python -m ipykernel install --user --name drlnd --display-name "drlnd"

7. Change the kernel of the Continuous_Control.ipynb notebook to match the drlnd environment by using the drop-down Kernel menu, and follow the instructions in the notebook to train the agent.