In reinforcement learning, what is the function that estimates the expected future reward given a specific state and action pair?

Question 1

In reinforcement learning, what is the function that estimates the expected future reward given a specific state and action pair?

a) Policy Function

b) Q-Function

c) Loss Function

d) Gradient Function

Question 2

b) Q-Function

In reinforcement learning, what is the function that estimates the expected future reward given a specific state and action pair?

Please log in or register to answer this question.

1 Answer