Train a Unity Environment (Banana field) using Double Dueling Q Network

Introduction

In this project, an agent is trained 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 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, the environment is considered solved when the trained agent achieves an average score of +13 over 100 consecutive episodes.

Getting Started

1. 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.

2. Place the file in the Udacity_RL_P1_D3QN GitHub repository and decompress the file.

3. Create a virtual environment and install the required libraries. For OSX users, you can use the MakeFile included in the repo. The option make all will create a new venv called Udacity_RL_P1 and install the relevant dependencies to execute the notebook.

4. Activate the virtual environment using source ./Udacity_RL_P1/bin/activate

5. Type jupyter lab and select Udacity_RL_P1 kernel.

Train and execute the model

Execute the notebook Navigation.ipynb. Initiate the Unity environment and the Agent. The last cell loads the default weights and executes the network. Set the flag train to TRUE to retrain the model. Further details can be found here