weicheng113 / p2_continuous-control

Continuous Control for Unity Reacher environment

Project 2: Continuous Control

Introduction

For this project, you will work with the Reacher environment.

Environment Description

States

• The observation space consists of 33 dimensions.
• It contains position, rotation, velocity, and angular velocities of the arm.

Actions

• Each action is a vector with four numbers.
• The numbers are corresponding to torque applicable to two joints.
• Every entry in the action vector is a number between -1 and 1.

Rewards

• A reward of +0.1 is provided for each step that the agent's hand is in the goal location.
• +0 Otherwise

Goal

• The goal of your agent is to maintain its position at the target location for as many time steps as possible.
• The environment is considered solved, when the average (over 100 episodes) of those average scores is at least +30.

Project Structure

The repository contains the following files.

• Continous_Control.ipynb Contains the agent training code for Unity Reacher environment.
• ddpg_agent.py Contains DDPG based agent implemenation.
• network.py Contains actor and critic network.
• noise.py Contians Ornstein-Uhlenbeck noise process utility class.
• replay_buffer.py Contains replay buffer utility class.

Getting Started

1. Install Anaconda(https://conda.io/docs/user-guide/install/index.html)
2. Install dependencies by issue:

pip install -r requirements.txt

3. 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.)

4. Place the file in the root folder, and unzip (or decompress) the file.

Instructions

Follow the instructions in Continuous_Control.ipynb to get started with training.