25 10 2023 E T

Pagina 1

Online Learning Applications Mock Exam Date Exam of Online Learning Applications Mock Exam Name: Surname: Student ID: Signature: Instructions: • The total number of points is 16. • The duration of the exam is: 2h00min. • During this exam you are not allowed to use books, notes, and electronic devices. • You are allowed to write the exam either with a pen or a pencil. • You are allowed to withdraw from the exam at any time. • Before you exit the room, you must hand in your exam. Online Learning Applications Mock Exam Date 1. (4 points) Answer the following questions about multi-armed bandits: • Explain the differences between full and bandit feedback • Explain the difference between stochastic and adversarial environments • In an stochastic environment, which algorithm has better performance between UCB1 and EXP3? • In an adversarial environment, which algorithm has better performance between UCB1 and EXP3? Online Learning Applications Mock Exam Date 2. (4 points) Answer the following questions about dynamic pricing: • Describe the properties of a dynamic pricing environment, e.g., the properties of the demand curve and action set • Describe an algorithm for dynamic pricing and its guarantees • How can you exploit information about the buyer (prior to setting the price)? Online Learning Applications Mock Exam Date 3. (4 points) Answer the following questions about truthful auctions: • Describe the second-price auction • Describe the parameters of an auction and which parameters are known to which agents • Describe an algorithm for online bidding in truthful auctions with a single slot Online Learning Applications Mock Exam Date 4. (4 points) Answer the following questions about combinatorial bandits: • Describe the combinatorial bandit framework • Show why the standard…