Project 1: Navigation

Introduction

For this project, we train an 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, the 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 RL_Navigation/ folder, and unzip (or decompress) the file.

Instructions

Follow the instructions in Navigation.ipynb to get started with training your own agent!
The dqn_agent.py contains the class for the agent that we would use for this project. It also contains the Replay Buffer class, which we use to add experiences to a memory buffer from which we sample experiences randomly. The model.py contains the Dueling Q Network that we would use as a function approximator.

If you want to use the pre-trained model, navigate to the model_weights folder and load the file dddqn.pth file.

Results

The environment gets solved in 467 episodes, achieving an average score of 13.03

Dependencies

Use the requirements.txt to install the required dependencies.

pip install -r requirements.txt

References

1. Double Deep Q-Learning https://arxiv.org/pdf/1509.06461.pdf
2. Dueling Network https://arxiv.org/pdf/1511.06581.pdf