Navigation Project of Udacity's Deep Reinforcement Learning Nanodegree
This programm contains my work for "Project 1: Navigation" of Udacity's Deep Reinforcement Learning Nanodegree.
The goal is to apply deep reinforcement learning techniques to train an agent to move through a virtual grid world and collect as many yellow bananas as possible (giving a reward of +1), while avoiding blue bananas (leading to a reward of -1). Overall, collecting >= 13 yellow bananas on the average across the last 100 episodes is required to succesfully complete this project.
Example actions taken by an trained agent as provided by Udacity's Deep Reinforcement Learning Nanodegree.
Instructions on who to complete this challenge are open ended. In this repository, the agent is implemented using a Double Deed Q-Learning Network (DDQN) as its policy in PyTorch. 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.
- You first need to configure a Python 3.6 / PyTorch 0.4.0 environment with the needed requirements as described in the Udacity repository
- Of course you have to clone this project and have it accessible in your Python environment
- Then you have to install the Unity environment as described in the Getting Started section (The Unity ML-agant environment is already configured by Udacity)
-
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 the DRLND GitHub repository, in the
p1_navigation/folder, and unzip (or decompress) the file.
To teach the agent, open an instance of Jupyter Notebook and exectute Main.ipynb. Follow instructions inside the notebook.