Practice Components Of An Mdp (2.1) - Reinforcement Learning and Decision Making

Practice: Components of an MDP

Lesson 2.1Reinforcement Learning and Decision Making

Practise this section

8 questions

Flashcard drill
5 cards from this section. Quick, good the night before a test.
Exercise
6 questions · about 4 min · pass mark 70%. Hints available.
Sign up to start the exercise
Quiz
2 questions · about 1 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What does the 'set of states (S)' represent in an MDP?
Show hintHide hint
Consider what each unique situation in the environment might be.
Question 2.
Define the 'set of actions (A)' in your own words.
Show hintHide hint
Think about the choices an agent can make.
3Question 3.
What does the set of states (S) represent?
- Possible actions of an agent
- Possible states of an agent
- Reward function
Show hintHide hint
Think about what characters might interact with in their environment.
4Question 4.
True or False: The discount factor (γ) influences how much an agent prioritizes future rewards.
- True
- False
Show hintHide hint
Recall that this factor can range from 0 to 1.
Question 5.
Create a real-world situation illustrating all components of an MDP, describe each one in detail.
Show hintHide hint
Think of the agent's objectives and potential obstacles.
Question 6.
Given a specific scenario, adjust the discount factor and analyze how it would affect the agent's long-term strategy.
Show hintHide hint
Consider how short-term vs. long-term planning would affect the decisions.

4 more questions in this section. Enroll free to practise them all.