Reinforcement Learning Resources

Courtesy of Zach Zhao.

Software

First, download and install the following software.

PyCharm - free, easy-to-use Python IDE. Used for writing Python programs.

Jupyter - tool for creating Python notebooks, with sharable visualizations and explanations.

Minimax

Minimax is an algorithm used to calculate the best move in a game. Check out this article to learn about the minimax algorithm. Or check out the video below.

Alpha-Beta

Go here to learn about alpha-beta pruning and check out this website for some practice.

The following is an example.

Monte-Carlo

Read this introduction to Monte Carlo search tries, and make sure you can parse through this implementation.