Project 1: Navigation

Introduction

This project trains an agent to navigate (and collect bananas!) in a large, square world.

The Environment

Unity Machine Learning Agents (ML-Agents) is an open-source Unity plugin that enables games and simulations to serve as environments for training intelligent agents. You can read more about ML-Agents by perusing the GitHub repository. One version of the Environments is bellow:

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 an 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

Step 1: Clone the DRLND Repository

Follow the instructions in the DRLND GitHub repository to set up your Python environment. These instructions can be found in README.md at the root of the repository. By following these instructions, you will install PyTorch, the ML-Agents toolkit, and a few more Python packages required to complete the project.

(For Windows users) The ML-Agents toolkit supports Windows 10. While it might be possible to run the ML-Agents toolkit using other versions of Windows, it has not been tested on other versions. Furthermore, the ML-Agents toolkit has not been tested on a Windows VM such as Bootcamp or Parallels.

Step 2: Download the Unity Environment

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.

Instructions

Follow the instructions in Navigation.ipynb to get started with training your own agent:

1. Start the Environment - if necessary change the file_name parameter to match the location of the Unity environment.
2. Examine the State and Action Spaces
3. Optionally take Random Actions in the Environment
4. Train the Agent (optionally you can skip to 5. Testing)
5. Test trained Agent

Further Modifications

For better performance you can modify:

1. Training process by modifying dqn function's arguments
   • n_episodes=5000,
   • eps_start=1.0,
   • eps_end=0.05,
   • eps_decay=0.995
2. Agent's hyper parameters in gqn_agent_Bananai.py
   • BUFFER_SIZE = int(1e6) # replay buffer size
   • BATCH_SIZE = 256 # minibatch size
   • GAMMA = 0.99 # discount factor
   • TAU = 1e-3 # for soft update of target parameters
   • LR = 0.001 # learning rate
   • UPDATE_EVERY = 8 # how often to update the network
3. Agent's QNetwork in model_Bananai.py