Project 1: Navigation

Introduction

For this project, I trained an DQN agent 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 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, your agent must get an average score of +13 over 100 consecutive episodes.

Getting Started

1. 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.

2. Place the file in the DRLND GitHub repository, in the p1_navigation/ folder, and unzip (or decompress) the file.

Installations

To be done.

Instructions

To be done.

Setup of Repository

Apart from the README.md file this repository consists of the following files:

1. Navigation.ipynb: An ipynb file for training the DQN agent and visualizing the training progress;
2. model.py: QNetwork class defining a DQN model;
3. ddpg_agent.py: Agent and ReplayBuffer classes; The Agent class makes use of the DQN model from model.py and the ReplayBuffer class;
4. checkpoint.pth: Contains the weights of the successful DQN model.

---

Todo List

Algorithm

• Replace ipynb with a py file
• Implement prioritized experience replay
• Implement double-DQN
• Implement dueling-DQN
• Fine Tune the hyperparameters
• Solve the environment with raw pixels

Analysis

• Improve visualization with seaborn package
• Compare three models using metrics from the Dueling DQN paper and under fair condition
• Provide in-depth discussion on experience replay vs. prioritized experience replay on this setting
• Provide in-depth discussion on DQN vs. double-DQN vs. dueling-DQN on this setting

Miscellaneous

• Add a requirement.txt file to the root directory
• Control the program with argparse
• Resize images in markdown files
• Add animations showing agents' performance
• Improve screen output information