What is the difference between Q-learning and SARSA?

Yes, this is the only difference. On-policy SARSA learns action values relative to the policy it follows, while off-policy Q-Learning does it relative to the greedy policy. Under some common conditions, they both converge to the real value function, but at different rates. Q-Learning tends to converge a little slower, but has the capabilitiy to … Read more

Why nextLine() and not nextString() ?

Consider this: nextLine return everything until next endline (\n) in form of String. Would you not think that you will retrieve everything if it was called nextString? In that case you would be posting question “why nextString() stops at endline” tl;dr it’s because it searches for endline (\n) upd: on documenatation it refers to it … Read more