Learn to use AI

Learning by reward

Learning by reward is a unit of 5 lessons in Rabbithole's Learn to use AI course, at level 2.

Lessons

1. Reinforcement learning: learning by rewardLevel 2
2. Policy gradient: learning the rule itselfLevel 2
3. Q-Learning: A Table of Action ScoresLevel 2
4. Deep Q-Learning: Swapping the Table for a NetworkLevel 2
5. Prediction-Based ExplorationLevel 2

Sources

These lessons draw on 5 sources. The most used:

• Lil'Log
• Hugging Face Deep RL Course
• MIT 6.S191: Introduction to Deep Learning (2026)
• Hugging Face LLM Course
• [1hr Talk] Intro to Large Language Models

All units in Learn to use AI