Exercise 5.3.2

Q-learning vs SARSA: off-policy vs on-policy control

Reinforcement Learning › Exercises › Lecture 5 · Model-Free Control › 5.3 Q-learning (off-policy learning)
EasyWritten

Why is \(Q\)-learning considered an off-policy control method? Conversely why is SARSA considered an on-policy control method?

Source: Sutton & Barto (2018), Reinforcement Learning: An Introduction, 2nd ed., Exercise 6.11. Licensed CC BY-NC-ND 2.0.