W1 Intro

Question 1

Reinforcement Learning. Which of the following statements is true?
A. Reinforcement Learning learns a function from labeled examples in a pre-existing dataset.
B. Reinforcement Learning uses a number to score the quality of a state.
C. Reinforcement Learning environments are always programmed in Gym.
D. Reinforcement Learning learns the inherent relations between items in a dataset.

Answer 1

B

Question 2

You are teaching an algorithm to choose the correct action based on the state of an environment. Because you are lacking a dataset of states and the correct action to choose, you are instantly updating your values based on the state and reward pairs you are receiving from the environment. What kind of learning is this?

Answer 2

Online RL