ellyanalinden / continuous_control

In this project, I solved the Reacher environment with a single agent. I used DDPG (Deep Deterministic Policy Gradient) algorithm.

Continuous Control - Unity ML-Agents Reacher Enivronment

Table of Contents

• Project description
• Goal
• Dependencies
• How to start
• Result

Project description

In this project, I solved the [Reacher] (https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Learning-Environment-Examples.md#reacher) environment with a single agent. I used DDPG (Deep Deterministic Policy Gradient) algorithm.

Goal

The agent must get an average score of +30 over 100 consecutive episodes.

Dependencies

• Python 3.6
• Numpy ("pip install numpy")
• PyTorch
• Reacher

How to run it

1. Clone this repo
2. To run this project locally, one must build their own environment. Below is the link to create local environment:
   • Linux: Click Here
   • Mac OSX: Click Here
   • Windows (32bit): Click Here
   • Windows (64bit): Click Here
3. Place above file in the same folder as this notebook's folder. Unzip/decompress the file.
4. Execute each cells in this notebook. The average score per 100 episodes will be shown after agent training is completed.

(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 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.)

Result