Quiz Space

Reinforcement Learning · Quiz 2 · 3 Dec 2023 · September 2023 term

Question 7: Which of the following is correct update rule for expecte…

Question 7

+2 marksOne correct option

Which of the following is correct update rule for expected SARSA:

  1. A
  2. B
  3. C
  4. D
  5. E
Show answer

Correct answer

  • A
See the whole paperTake it as a mock test

Question 7 of 21 in the IIT Madras BS Reinforcement Learning (Reinforcement Learning) Quiz 2 paper sat on 3 Dec 2023, in the September 2023 term (IIT M DEGREE AN2 EXAM QDB2 03 Dec 2023). It carries 2 marks.

More questions from this paper

  1. Q1Note: For numerical answer type questions, always enter your answer correct upto two decimal places without rounding up…
  2. Q2What is the estimate of V (B) returned by first-visit MC?\ Note: For numerical answer type questions, always enter your…
  3. Q3What is the estimate of V (A) returned by first-visit MC?\ Note: For numerical answer type questions, always enter your…
  4. Q4What is the estimate of V (B) returned by batch TD(0)?\ Note: For numerical answer type questions, always enter your an…
  5. Q5What is the estimate of V(A) returned by batch TD(0)?\ Note: For numerical answer type questions, always enter your ans…
  6. Q6Figure question
  7. Q8Choose the correct option:
  8. Q9Consider the following and select the correct option.\ Assertion: Double Q learning removes or minimizes maximization b…
  9. Q10Identify the correct Q function estimated by Dueling DQN?
  10. Q11What is the advantage of computing n^(th) step reward vs 1-step reward?
  11. Q12Select correct statements regarding eligibility traces:
  12. Q13What are the Q values for all the actions (i.e. left, up, right, down in that order) in state s1?
  13. Q14What is the TD(0) target (Q-learning) for this transition?\ Note: For numerical answer type questions, always enter you…
  14. Q15Note: For numerical answer type questions, always enter your answer correct upto two decimal places without rounding up…
  15. Q16Training a neural network with TD target, can diverge because:
  16. Q17Suppose we are using a policy gradient method to solve a reinforcement learning problem. Assuming that the policy retur…
  17. Q18What are the advantages of policy search methods over other approaches?
  18. Q19Which of the problems does the replay buffer solve regarding training a Q-network?
  19. Q20Which of the following is the correct way to represent policy for policy search methods? Assume θ represents a real val…
  20. Q21Which of the following is the correct way to represent policy for policy search methods?