Skip to content
Implemented DDPG to solve Unity's Reacher environment
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Project 2

This project was done as part of the Udacity Deep Reinforcement Nanodegree. Some of the text in this README is adapted from the original Udacity Deep Reinforcement Learning Nanodegree repo. Read Report.pdf for more information.


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. Make sure you have the following python library dependencies:

    • pytorch
    • numpy
    • unityagents
    • matplotlib
    • jupyter notebook
  2. Clone this repository with the command git clone or simply download as a zip folder by using the green button labeled 'clone or download' on this page. Note that there is no need to separately download the Unity environment. The necessary files are included in the repo.


Run jupyter notebook and open project2.ipynb.

You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.