WorksheetsReinforcement Learning-Unit-1
Total questions: 15
Worksheet time: 8mins
Reinforcement learning is a ____
Prediction-based learning technique
Feedback-based learning technique
History results-based learning technique
Clustering based learning technique
Which kind of data does reinforcement learning use?
Labeled data
UnLabeled data
None
Both
Reinforcement learning methods learned through ____?
Experience
Predictions
Analyzing the data
Classifying the data
Which of the following is the practical example of reinforcement learning?
House pricing prediction
Market basket analysis
Text classification
Driverless cars
What is an agent in reinforcement learning?
Agent is the situation in which rewards are being exchanged
Agent is the simple value in reinforcement learning.
An agent is an entity that explores the environment.
An agent is a model in reinforcement learning
What is the environment in reinforcement learning?
Environment is a situation that is based on the current state
Environment is a situation in which an agent is present.
Environment is similar to feedback
Environment is a situation that the agent returns as a result.
What is the state of reinforcement learning?
State is a situation in which an agent is present.
A state is the simple value of reinforcement learning.
A state is a result returned by the environment after an agent takes an action.
A state is a value that represents the reward
How many elements does reinforcement learning consist of?
2
3
4
5
The agent's main objective is to ____the total number of rewards for good actions.?
Minimize
Maximize
Null
Reinforcement learning is defined by the ____?
Policy
Reward Signal
Value Function
Model of the environment
On which of the following elements of reinforcement learning, the reward that an agent can expect is dependent?
Policy
Reward Signal
Value Function
Model of the environment
Which of the following elements of reinforcement learning imitates the behavior of the environment?
Policy
Reward Signal
Value Function
Model of the environment
Consider the following statements for ϵ-greedy approach for a stationary environment:
i Always keeping ϵ as constant is a good approach
ii Large values of ϵ will lead to unnecessary exploration in the long run
iii Cooling down ϵ too fast is problematic as it cannot guarantee correctness in value estimates
Which of the above statements is/are correct?
i, ii, iii
only iii
only ii
ii, iii
Which among the following are features of a reinforcement learning solution to a learning problem? (i) trial and error approach to learning
(ii) exploration versus exploitation dilemma
(iii) learning based on rewards
(iv) absence of any feedback or supervision
(iv)
ii, iii
i, ii, iii
iii
Consider the following statements
(i) The rewards are obtained at a fixed time after taking an action.
(ii) Reinforcement Learning is neither supervised nor unsupervised learning.
(iii) Two reinforcement learning agents can learn by playing against each other.
(iv) Always selecting the action with maximum reward will automatically maximize the winning probability in a game.
Which of the above statements is/are correct?
i, ii, iii
ii
ii, iii
iii, iv
