Practice Markov Decision Process (mdp) (2) - Reinforcement Learning and Decision Making

Practice: Markov Decision Process (MDP)

Lesson 2Reinforcement Learning and Decision Making

Practise this section

10 questions

Flashcard drill
4 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
4 questions · about 3 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What does MDP stand for?
Show hintHide hint
Think of a term used in decision-making frameworks.
Question 2.
Name one component of an MDP.
Show hintHide hint
These components help define decision-making frameworks.
3Question 3.
What does the discount factor (γ) indicate in an MDP?
- Only the immediate rewards
- Entirely future rewards
- Importance of future rewards versus immediate rewards
Show hintHide hint
It's a number between 0 and 1.
4Question 4.
True or False: The states in an MDP represent only the current conditions of the agent at any moment.
- True
- False
Show hintHide hint
Think about different possible conditions.
Question 5.
Using the Bellman Equation, devise a strategy for a simple maze navigation task where states are intersections, actions are moving forward/backward/turning, and rewards are given for reaching the exit. Include probabilities based on the agent's movement accuracy.
Show hintHide hint
Consider if the agent has a 75% success rate - how does this affect P?
Question 6.
Design an MDP for a delivery drone with states representing locations, actions concerning flight paths, and rewards that vary based on package delivery efficiency. How would you configure the transition probabilities?
Show hintHide hint
Think about real-life variables affecting the drone's flight.

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