Reinforcement Learning MCQs

1.     _________________ is a type of machine learning in which an agent learns to make decisions by interacting with an environment.

 

A. Supervised learning

B. Reinforcement learning

C. Semi-supervised learning

D. Unsupervised learning

Ans: B

 

2. Which of the following are applications of Reinforcement learning?

 

A. Robotics

B. video games

C. self-driving cars

D. All of the above

Ans: D

 3._________________ is defined as when an event, occurs due to a particular behavior, increases the strength and the frequency of the behavior.

 

A. Positive Reinforcement

B. Negative Reinforcement

C. Both A and B

D. None of the above

Ans : A

 

4. Which type of feedback does an agent in reinforcement learning receive?

A. Predictions
B. Labels
C. Clusters
D. Rewards or penalties

Ans: D

 5. ______________ is the Q-learning algorithm used for in reinforcement learning.

 

A. Image recognition

B. Clustering

C. Finding the optimal decision-making strategy

D. Natural language processing

Ans: C

 6. Which of the following are Advantages of reinforcement learning?

 

A. Maximizes Performance

B. Sustain Change for a long period of time

C. Too much Reinforcement can lead to an overload of states which can diminish the results

D. All of the above

Ans: D

 7.  In Reinforcement learning, the decision is made on the initial input or the input given at the start

  A. TRUE

B. FALSE

C. Can be true or false

D. Can not say

 Ans : B

 8. Which of the following is true about reinforcement learning?

 A. The agent gets rewards or penalty according to the action

B.    The agent navigates in an environmental building the example experiences or the training dataset.

C.    The target of an agent is to maximize the rewards and minimize the penalty.

D.    All of the above

Ans: D

 9. Q-Learning algorithm is off-policy algorithm because

A.    Policy being trained is exactly the one being executed

B.    Policy being trained is not necessarily the one being executed.
There is nothing called Q-Learning algorithm but Q-Value Iteration

D.    None of the above

Ans: B

 10. In Reinforcement learning decision is dependent, So we give labels to sequences of dependent decisions.

 

A. TRUE

B. FALSE

C. Can be true or false

D. Can not say

Ans: A