Q-Learning - Model Free Reinforcement Learning and Temporal Difference Learning
Steve Brunton via YouTube
Overview
This course covers Q-learning, a popular method in reinforcement learning, and its connection to temporal difference learning. Students will learn about other TD algorithms like SARSA and their relationship to biological learning through dopamine. The course also explores Q-learning as a common framework for deep reinforcement learning. The teaching method involves a lecture format, and the intended audience includes learners interested in reinforcement learning, machine learning, and control systems.
Syllabus
Introduction
Recap
Monte Carlo Learning
Temporal Difference Learning
QLearning
SARSA
Off Policy
Conclusion
Taught by
Steve Brunton