In this project an agent is trained to navigate (and collect bananas!) in a large, square world provided by a unity environment. As training algorithm for the agent serves Deep Q-Network.
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 the 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, the agent must get an average score of +13 over 100 consecutive episodes.
-
Configure a new conda virtual environment for Python 3.6 with the needed requirements as described in this Udacity repository.
-
Install Unity Agents using:
pip install unityagents -
The environment provided with this repository is for Mac OS. If you have another OS than please use one of the following links to donwload the environment for your OS replacing the "Banana.app" in this repository.
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.
Follow the instructions in Solution.ipynb to get started with training your own agent!