rmoin / continuouscontrol

DDPG Reinforcement Learning Implementation. Used to solve Unity Reacher Environment

Continuous Control

Introduction

For this implementation, we 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 our 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

We will use 20 identical agents, each with its own copy of the environment.

Solving the Environment

We need to take into account the presence of many agents. In particular, our 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 the repository.

git clone https://github.com/rmoin/ContinousControl.git

2. Download the environment from one of the links below. We 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 the GitHub repository, in the ContinousControl/ folder, and unzip (or decompress) the file.

Instructions

Follow the instructions in Continuous_Control.ipynb to get started with training our own agent!

Dependencies

To set up your python environment to run the code in this repository, follow the instructions below.

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. Download python folder from here and place in the Github repository, in the ContinousControl/ folder. Now go to the python/ folder. Then, install several dependencies.

cd ContinousControl/python
pip install .

4. Create an IPython kernel for the drlnd environment.

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

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