In this project, an agent navigates in a large, square world and collects bananas.
Click on the image below to see the solution demo:
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.
-
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 root of the folder and unzip the file.
-
Run all the cells in Navigation.ipynb to test the environment.
To train the agent run all the cells in Navigation_DQN.ipynb notebook.
Description of the implementation is provided in report.md. For technical details see the code in the notebook.
Model weights are stored in dqn.pth