University of Toronto ECE 1508
Professor Bereyhi · University of Toronto · 1 lecture with notes
Students in this class: ask your lecturer for the class code, and these lectures will already be in your library when you sign up.
RL @ ECE-UofT - Lecture 05: Deep Bootstraping and epsilon-Greedy Improvement
N-step TD and TD(λ) trade off bias and variance; eligibility traces make learning online, while ε-greedy control preserves exploration.