For this project, an agent trains 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 agent is to collect as many yellow bananas as possible while avoiding blue bananas in a max 300 steps.
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, agent must get an average score of +13 over 100 consecutive episodes.
-
Clone this GitHub repository (p1_navigation). If you do not use Linux, go to step 2., if you do, go to step 4.
-
Download the environment from one of the links below. You need only select the environment that matches your operating system:
- 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 this GitHub repository, in the
p1_navigation/folder, and unzip (or decompress) the file and delete Banana_Linux folder. -
Open new terminal and run your virtual environment with Python3 :
$source activate drlnd -
In terminal, place yourself inside of p1_navigation folder
-
Run notebook:
$jupyter notebook Navigation.ipynb
Follow the instructions in Navigation.ipynb to get started with training your own agent!