Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/amorehead/mlforeveryone
A series of tutorials on learning Machine Learning using the Python programming language, for everyone!
https://github.com/amorehead/mlforeveryone
Last synced: 13 days ago
JSON representation
A series of tutorials on learning Machine Learning using the Python programming language, for everyone!
- Host: GitHub
- URL: https://github.com/amorehead/mlforeveryone
- Owner: amorehead
- License: mit
- Created: 2022-05-22T02:30:59.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-08-01T19:45:32.000Z (over 2 years ago)
- Last Synced: 2024-05-14T00:22:52.901Z (6 months ago)
- Language: Jupyter Notebook
- Size: 13.8 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# MLForEveryone
[](https://www.python.org/downloads/release/python-380/)
A series of tutorials on learning Machine Learning using the Python programming language, for everyone!
Image Credit: [Towards Data Science](https://towardsdatascience.com/machine-learning-algorithms-in-laymans-terms-part-1-d0368d769a7b)
## Course objectives
By the end of this course, one will:
1. Master the fundamentals of writing Python scripts
2. Gain an understanding of the fundamental concepts in machine learning
3. Employ Python to train machine learning models using either supervised learning, unsupervised learning, or reinforcement learning
## Tutorials
To begin this course, as desired, open up the Jupyter notebooks in the `notebook_tutorials` directory. For example, currently you can choose from:
Introduction to Machine Learning
Introduction to Deep Reinforcement Learning
## Capstone Project
This course includes a capstone project to give students the opportunity to apply the knowledge they have acquired in an exciting setting, development of video game agents using deep reinforcement learning. The project currently available to students is as follows.
### MineRL
MineRL (pronounced like "mineral") is a Python package that allows one to develop intelligent software agents to play Minecraft, a popular sandbox video game available on a variety of platforms. Below are instructions for how to install MineRL on a machine running the Windows operating system.
#### Installation
##### Downloading and customizing required software
1. Install Python 3.8 (if not done previously)
2. Install Anaconda (if not done previously)
3. Install Git for Windows (if not done previously)
4. Install Oracle's JDK 8
5. Add `C:\Program Files\Java\jdk1.8.0_341\bin` and `C:\Program Files\Git\bin` to the top of your system's PATH variable accessible via `Advanced System Settings`
##### Creating and configuring a local Conda environment
Now, create and configure your Conda environment using your `Anaconda Command Prompt` search result:
```bash
# Set up Conda environment locally
conda create --name MLForEveryone python=3.8
# Activate Conda environment located in the current directory:
conda activate MLForEveryone
# Install MineRL as a Python package inside your new `MLForEveryone` Conda environment
pip install git+https://github.com/minerllabs/[email protected]
```
##### Verifying the installation was successful
Finally, test your MineRL installation with the following command(s).
```bash
# Download a copy of this GitHub repository
git clone https://github.com/amorehead/MLForEveryone.git
# Move to the directory containing the capstone project's script
cd MLForEveryone/capstone_project/
# Run a test script for MineRL
python random_minerl_agent.py
```
##### Training your first reinforcement learning agent to play Minecraft!
To train an agent to play Minecraft by turning observations of the pixels on the game's screen into actions to take in the game, see the below Google Colab notebook curated by the makers of MineRL.