Deep RL - Navigation

• Organization: Udacity
• Course: Deep Reinforcement Learning NanoDegree.
• Project: #1 - Navigation

Project Details

For this project, we will train an agent to navigate (and collect bananas!) in a large, square world.

A reward of +1 is provided for collecting a yellow banana, and a reward of -1 is provided for collecting a blue banana. Thus, the goal of our agent is to collect as many yellow bananas as possible while avoiding blue bananas.

The state space has 37 dimensions and contains the agent's velocity, along with ray-based perception of objects around agent's forward direction. Given this information, the agent has to learn how to best select actions. Four discrete actions are available, corresponding to:

• 0 - move forward.
• 1 - move backward.
• 2 - turn left.
• 3 - turn right.

The task is episodic, and in order to solve the environment, our agent must get an average score of +13 over 100 consecutive episodes.

Getting Started

1. Clone this repository

2. 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

   (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 environment.

3. Place the file in the root folder of the cloned repository, and unzip (or decompress) the file.

Instructions

Code

UdacityDRLNavigation/
  |- .gitignore
  |- agent.py
  |- checkpoint.pth
  |- dqn.py
  |- model.py
  |- README.md
  |- REPORT.md
  |- test.py
  |- train.py
  |- train_scores.png

• .gitignore - Gitignore file
• agent.py - Navigation agent, interacts with and learns from the environment.
• checkpoint.pth - Trained model's state
• dqn.py - Deep Q Network class (train and test code)
• model.py - Actor (Policy) Model.
• README.md - this readme file
• REPORT.md - Implementation description
• test.py - Test the agent
• train.py - Train the agent
• train_scores.png - Training progress plot

Train

$ python train.py

Test

$ python test.py