III Year II Sem, Mid 1 Question Paper
Reinforcement Learning
Unit 1
Q.No
Questions
Marks
CO
KL
1
Define Reinforcement Learning and explain how it differs
from supervised and unsupervised learning.
10
1
L2
2
Explain the key elements of a Reinforcement Learning
system with a neat diagram.
10
1
L2
3
Describe the Tic-Tac-Toe problem as an extended example
of Reinforcement Learning.
10
1
L2
4
Trace the history and development of Reinforcement
Learning.
10
1
L2
5
What are some real-world examples of Reinforcement
Learning applications?
5
1
L1
6
Define Reinforcement Learning and explain limitations of
RL.
5
1
L1
7
List out the elements used in Reinforcement Learning.
5
1
L1
8
Define 'state,' 'action,' and 'reward' within an RL framework.
5
1
L1
Unit 2
Q.No
Questions
Marks
CO
KL
1
Describe action-value methods used for solving multi-arm
bandit problems.
10
2
L2
2
What is a nonstationary bandit problem? Explain
methods to track it.
10
2
L2
3
Explain the Upper-Confidence-Bound (UCB) action
selection method.
10
2
L2
4
Explain the Gradient Bandit algorithm with suitable
equations.
10
2
L2
5
What is Associative Search or Contextual Bandit problem
5
2
L1
6
Write the action selection formula for the UCB algorithm
5
2
L1
7
What is non-stationary bandit problem
5
2
L1
8
What is exploration-exploitation dilemma
5
2
L1