Project 2: Continuous Control

Introduction

For this project, you will work 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.

Distributed Training

For this project, we will provide you with two separate 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.

Solving the Environment

Note that your project submission need only solve one of the two versions of the environment.

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).

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

---

(OPTION 2 WAS CHOSEN)

Requirements

• Conda
• jupyter-notebook

Getting Started

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. Clone the drl repository ( https://github.com/udacity/deep-reinforcement-learning).

git clone https://github.com/udacity/deep-reinforcement-learning.git

3. Clone this repository, replace requirements.txt in dlr repository file with requirements.txt file from this repository. (To fix Dependency issues for Tensorflow, Torch, ...) Then install dependencies.

git clone https://github.com/luctrate/p2_continuous-control.git
cp p2_continuous-control/requirements.txt deep-reinforcement-learning/python/requirements.txt 
cd deep-reinforcement-learning/python/
pip install .

4. Create an IPython kernel for the drlnd environment and then change directory o this repository.

python -m ipykernel install --user --name drlnd --display-name "drlnd"
cd ../../p2_continuous-control/

5. Download the environment from one of the links below. You need only select the environment that matches your operating system: - Linux: click here - Mac OSX: click here - Windows (32-bit): click here - Windows (64-bit): click here

6. Place the file in this GitHub repository, in the root folder, and unzip (or decompress) the file.

7. Open Jupyter notebook.

jupyter-notebook

The browser should open a new tab with jupyter opened. If not check console output.

6. Before running code in a notebook, change the kernel to match the drlnd environment by using the drop-down Kernel menu.

---

Instructions

Follow the instructions in Continuous_Control.ipynb to use the trained agent or train the agent from sratch.