By using this site, you agree to the Terms of Use that are defined in LICENSE.
The goal of this project is to train a so-called intelligent agent to navigate a virtual world (or environment), and collect as many yellow bananas as possible while avoiding blue bananas.
This project was developed in partial fulfillment of the requirements for Udacity's Deep Reinforcement Learning Nanodegree program.
According to skymind.ai, the term Reinforcement Learning (RL) refers to:
Goal-oriented algorithms, which learn how to attain a complex objective (goal) or how to maximize along a particular dimension over many steps; for example, they can maximize the points won in a game over many moves. RL algorithms can start from a blank slate, and under the right conditions, they achieve superhuman performance. Like a pet incentivized by scolding and treats, these algorithms are penalized when they make the wrong decisions and rewarded when they make the right ones – this is reinforcement.
Deep Reinforcement Learning (DRL) combines Artificial Neural Networks (ANNs) with an RL architecture that enables software-defined agents to learn the best actions possible in virtual environment in order to attain their goals. That is, it unites function approximation and target optimization, mapping state-action pairs to expected rewards.
The project development environment is based on Unity's Machine Learning Agents Toolkit (ML-Agents). The toolkit is an open-source Unity plugin that enables games and simulations to serve as environments for training intelligent agents.
The project environment is similar to, but not identical to the Banana Collector environment on the Unity ML-Agents GitHub page.
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 the 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 the 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.
At first, you need to 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.
For this project, you will not need to install Unity - this is because Udacity has already built the environment for you (for convenience), and you can download it from one of the links below. You need only select the environment that matches your operating system:
- Linux click here.
- macOS click here.
- Windows (32-bit) click here.
- Windows (64-bit) click here.
Then, place the file in the p1_navigation/ folder in the DRLND GitHub repository (provided that you have already completed Step 1), and unzip (or decompress) the file.
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.
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 "headless" version of the environment. You will not be able to watch the agent without enabling a virtual screen, but you will be able to train the agent.
To watch the agent, you should follow the instructions to enable a virtual screen, and then download the environment for the Linux operating system above.
After you have followed the instructions above, open Navigation.ipynb (located in the p1_navigation/ folder in the DRLND GitHub repository) and follow the instructions to learn how to use the Python API to control the agent.
In the last code cell of the Navigation.ipynb notebook, you'll learn how to design and observe an agent that always selects random actions at each time step. The goal of this project is to create an agent that performs much better!
See REPORT.md for a detailed attempts made to solve the challenges presented. Feel free to use the code and notebooks in this repo for learning purposes, and perhaps to beat the attempts mentioned in the report.