In this project, an agent navigates in a large, square world and collects bananas.

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, and in order to solve the environment, an agent must get an average score of +13 over 100 consecutive episodes.


Installation:

Download the environment from one of the links below. You need only select the environment that matches your operating system:

Linux: https://s3-us-west-1.amazonaws.com/udacity-drlnd/P1/Banana/Banana_Linux.zip
Mac OSX: https://s3-us-west-1.amazonaws.com/udacity-drlnd/P1/Banana/Banana.app.zip

For windows users, go to the apple store and buy a mac and read through installation again


Place the file in root of the folder and unzip the file.

Running:

Run all the cells in Navigation.ipynb to train the agent and see how he performs