Quiz Space

Reinforcement Learning · End Term · 10 May 2026 · January 2026 term · Set 1

Question 18: What is the key advantage of Intra-Option Q-Learning (Al…

Question 18

+2 marksOne correct option

What is the key advantage of Intra-Option Q-Learning (Algorithm B) over SMDP Q-Learning (Algorithm A)?

  1. A
  2. B
  3. C

    It converges to a globally optimal policy, whereas SMDP Q-learning only converges locally

  4. D

    It eliminates the need for a high-level policy by learning all options simultaneously

Show answer

Correct answer

  • B
See the whole paperTake it as a mock test

Question 18 of 20 in the IIT Madras BS Reinforcement Learning (Reinforcement Learning) End Term paper sat on 10 May 2026, in the January 2026 term (Reinforcement Learning 10 May 26 (Session 2)). It carries 2 marks.

More questions from this paper

  1. Q1Figure question
  2. Q2Figure question
  3. Q3DDPG uses an experience replay buffer. What is the direct consequence of using an experience replay buffer
  4. Q4Compared to the policy gradient, the DPG theorem requires integration over:
  5. Q5Figure question
  6. Q6Which are known limitations or failure modes of DDPG?
  7. Q7Figure question
  8. Q8Recall standard control algorithms in RL, like Q-Learning, SARSA, Expected SARSA, etc., involve a maximisation step in …
  9. Q9Figure question
  10. Q10Round your final answer to 2 decimal places.
  11. Q11Why is DPG generally more sample-efficient than SPG in high-dimensional continuous action spaces?
  12. Q12Ganesh’s on-policy DPG implementation is likely to suffer from which of the following problems? Select all that apply.
  13. Q13Figure question
  14. Q14Figure question
  15. Q15The REINFORCE gradient estimator is: Why does REINFORCE exhibit high gradient variance, particularly in long-horizon ta…
  16. Q16The REINFORCE gradient estimator is:
  17. Q17The REINFORCE gradient estimator is:
  18. Q19Figure question
  19. Q20Figure question