This repo gives will train an agent to navigate (and collect bananas!) in a large, square world. This is similar to Unity's Banana Collector environment.
The agent is trained using a Deep Q Network (DQN), which we will describe in the following sections.
The game is very simple. As we collect yellow bananas, a reward of +1 is provided, and a reward of -1 for collecting blue bananas. 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, your agent must get an average score of +13 over 100 consecutive episodes.
-
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.
-
Place the file in your cloned repository, and unzip (or decompress) the file.
-
Run
pip install -r requirements.txtto install all required python libraries needed to run this project locally. We suggest that you create a virtual environment first. To do this, using python'svirtualenvpackage, follow the instructions here.