
Reinforcement Learning Quiz 2: 6 August 2023 (May 2023 term)
The IIT Madras BS Reinforcement Learning (Reinforcement Learning) Quiz 2 paper sat on 6 Aug 2023, in the May 2023 term: 12 questions for 50 marks in 120 minutes. Every question is below with its answer. Take it as a timed mock test to be marked, or read it through first.
- 12
- 50
- 120 min
- 6
- 2
- 4
Show answer
Correct answer
Question 2
Show answer
Correct answer
Question 3
Which of the following is the statement of the policy gradient theorem?
Show answer
Correct answer
Question 4
Show answer
Correct answer
Question 5
Select all on-policy control algorithms from the options given below.
Q learning
Double Q learning
SARSA
Expected SARSA
Show answer
Correct answers
SARSA
Expected SARSA
Question 6
Algorithm-1 is an implementation of SARSA
Algorithm-2 is an implementation of SARSA
Both algorithms are correct implementations of SARSA
Algorithm-1 is an implementation of Q-learning
Algorithm-2 is an implementation of Q-learning
Both algorithms are correct implementations of Q-learning
Show answer
Correct answer
Algorithm-1 is an implementation of SARSA
Question 7
Show answer
Correct answer: 1
Question 8
Show answer
Correct answer: 5
Question 9
Show answer
Correct answer: 1.24 (accepted within ±0.01)
Question 10
Show answer
Correct answer
Question 11
Show answer
Correct answer: 7
Question 12
Show answer
Correct answer