- Subject: Machine learning, Reinforcement Learning
- Audience: High school with basic coding knowledge (variables, conditionals, loops, and functions)
- Authors: Michael Megliola and Jeff Gunn
- URL: http://loislab.org
Description:
Free online course introduces concepts of probability and expected reward, then moves on to the Q-learning algorithm and applies it to maze solving and playing tic-tac-toe. The course is organized as a Jupyter notebook that runs in the browser. It offers clear explanations and a logical development of topics, and is not Python-heavy; it is accessible to any student familiar with basic coding constructs (variables, conditionals, loops, and functions). No math beyond Alegbra 2.High school with basic coding knowledge (variables, conditionals, loops, and functions)