Quiz Space

Reinforcement Learning · Quiz 2 · 16 Mar 2025 · January 2025 term

Question 4: What is a key advantage of using n-step TD prediction ove…

Question 4

+2 marksOne correct option

What is a key advantage of using n-step TD prediction over one-step TD prediction?

  1. A

    n-step TD prediction requires less memory and computational resources.

  2. B

    n-step TD prediction can handle delayed rewards and credit assignment over multiple time steps.

  3. C

    n-step TD prediction converges faster to the optimal policy.

  4. D

    n-step TD prediction guarantees convergence to the optimal value function for any choice of the learning rate.

Show answer

Correct answer

  • B

    n-step TD prediction can handle delayed rewards and credit assignment over multiple time steps.

See the whole paperTake it as a mock test

Question 4 of 22 in the IIT Madras BS Reinforcement Learning (Reinforcement Learning) Quiz 2 paper sat on 16 Mar 2025, in the January 2025 term (IIT M DEGREE AN EXAM QDB2 16 Mar 2025). It carries 2 marks.

This question was also asked in

More questions from this paper

  1. Q1For on policy SARSA update rule for Q(s, a), s, a, s′, a′ are needed. When is a′ computed/sampled?
  2. Q2Figure question
  3. Q3Figure question
  4. Q5Consider a reinforcement learning agent navigating a complex environment with sparse rewards. Which of the following st…
  5. Q6Figure question
  6. Q7Figure question
  7. Q8What is the estimate of V (B) returned by first-visit MC?
  8. Q9What is the estimate of V (A) returned by first-visit MC?
  9. Q10What is the estimate of V (B) returned by batch TD(0)?
  10. Q11What is the estimate of V (A) returned by batch TD(0)?
  11. Q12V (s) is a linear function approximator.
  12. Q13Based on the above data, answer the given subquestions.
  13. Q14Based on the above data, answer the given subquestions.
  14. Q15Based on the above data, answer the given subquestions.
  15. Q16Based on the above data, answer the given subquestions.
  16. Q17Based on the above data, answer the given subquestions.
  17. Q18Based on the above data, answer the given subquestions.
  18. Q19Based on the above data, answer the given subquestions.
  19. Q20What is the value of d (i.e. the length of the discretized state vector)?
  20. Q21Based on the above data, answer the given subquestions.
  21. Q22Based on the above data, answer the given subquestions.