Reinforcement Learning Project 1: Banana Hunter

Introduction

For this project, you will utilize value-based methods in reinforcement learning(RL) to train an agent (a banana hunter) to navigate in a large, square world, collecting yellow bananas while avoiding blue bananas.

Calculating Rewards

A reward of +1 is provided for collecting a yellow banana, and a reward of -1 is provided for collecting a blue banana. The goal of the agent is to collect as many yellow bananas as possible while avoiding blue bananas.

The Environment

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, the agent must get an average score of +13 over 100 consecutive episodes.

Project folders and files

Folder structure:

root
- p1_navigation
- python

The Report.ipynb notebook can be used to train the agents

The agents are defined in the files:

• dqn_agent.py: vanilla DQN agent
• doubledqn_agent.py: double DQN agent
• prioritized_ddqn.py: double DQN agent with prioritized experience replay
• dueling_ddqn.py: double DQN agent with prioritized experience replay using a dueling network

The PyTorch Neural Networks are defined in the files:

• model.py: default DQN network
• dueling_model.py: Dueling DQN network

The saved pytorch model weights are also saved in root

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

Dependencies

To set up your python environment to run the code in this repository, follow the instructions below.

1. Create (and activate) a new environment with Python 3.6.

   • Linux or Mac:

   conda create --name dqn python=3.6
   source activate drlnd

   • Windows:

   conda create --name drlnd python=3.6 
   activate drlnd

2. Follow the instructions in this repository to perform a minimal install of OpenAI gym.

   • Next, install the classic control environment group by following the instructions here.
   • Then, install the box2d environment group by following the instructions here.

3. Clone the repository (if you haven't already!), and navigate to the python/ folder. Then, install several dependencies.

git clone https://github.com/udacity/deep-reinforcement-learning.git
cd deep-reinforcement-learning/python
pip install .

4. Create an IPython kernel for the drlnd environment.

python -m ipykernel install --user --name drlnd --display-name "drlnd"

5. Before running code in a notebook, change the kernel to match the drlnd environment by using the drop-down Kernel menu.

Instructions

You can run the code in Report.ipynb to train several versions of the agents. Pretrained models are also saved in the root folder (checkpoints) and can be loaded directly if needed.

(For AWS) If you'd like to train the agent on AWS, you must follow the instructions to set up X Server, and then download the environment for the Linux operating system above.