Learning from Pixels

Introduction

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 your agent is to collect as many yellow bananas as possible while avoiding blue bananas.

The state is an 84 x 84 RGB image, corresponding to the agent's first-person view. 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, your agent must get an average score of +13 over 100 consecutive episodes.

Getting Started

1. Install packages required to working the code:

   • Python 3.6
   • pip install unityagents Unity Machine Learning Agents (ML-Agents)
   • PyTorch (The code works with both CPU and GPU that is capable of running CUDA)
   • NumPy, Matplotlib, Pandas

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.

3. Place the file in folder with other repository files, and unzip (or decompress) the file.

Note: The project environment is similar to, but not identical to the Banana Collector environment on the Unity ML-Agents GitHub page.

Instructions

The repository contains four files and one directory:

• double_dqn_agent.py: DDQN agent with Experience replay
• model.py: CNN model
• Navigation_Pixels.ipynb: The code to explore the environment and train an agent
• checkpoint: Saved trained model weights of the successful agent as a multipart ZIP file
• Report.md: Description of implementation

Follow the instructions in Navigation_Pixels.ipynb to get started with training an agent.