Challenge: Multi-Armed Bandits

From this point onward, you will receive coding challenges in Jupyter Notebook format. If you know how to properly setup the environment for such notebooks, feel free to do so. However, we recommend you to use Google Colab, as it offers many advantages over plain Jupyter notebooks. Read this article to learn how Colab works.

Note

Verifying the correctness of your solution can be tricky, and errors may occur. If you're confident that your solution is correct but it's marked as incorrect, review the recommended solution carefully. If you still can't identify any issues, try implementing the recommended solution in a separate cell and run it.

How to Open the Notebook and Complete the Tasks?

To open the notebook and complete the tasks, you should follow these steps:

Download the notebook: you can find the download button at the bottom of this page;
Open Google Colab: open the website and login with your Google account;
Open the notebook: use File > Upload notebook or File > Open notebook > Upload and choose the file you downloaded. If you want to continue working on your tasks after a break, use File > Open notebook > Recent and find your notebook in that window;
Follow the instructions: the notebook will contain detailed instructions to the tasks. You should read them before proceeding to the tasks;
Receive the key: after solving each task, you will receive a part of the key, necessary to complete the chapter. Enter these parts inside of a quiz on the bottom of the page after you finish the challenge to verify that you completed all tasks.

Challenge

Oliko kaikki selvää?

Kiitos palautteestasi!

Osio 2. Luku 6

Kysy tekoälyä

Kysy mitä tahansa tai kokeile jotakin ehdotetuista kysymyksistä aloittaaksesi keskustelumme

Kurssisisältö

Introduction to Reinforcement Learning

1. RL Core Theory

What is RL?RL vs Other Learning Paradigms Markov Decision Process Episodes and Returns Model, Policy, and Values Exploration vs Exploitation Gymnasium Basics Challenge: Setting Up an Environment

2. Multi-Armed Bandit Problem

Problem Introduction Action Values Epsilon-Greedy Algorithm Upper Confidence Bound Algorithm Gradient Bandits Algorithm Challenge: Multi-Armed Bandits

3. Dynamic Programming

What is Dynamic Programming?Bellman Equations Optimality Conditions Policy Evaluation Policy Improvement Generalized Policy Iteration Policy Iteration Value Iteration Challenge: Dynamic Programming

4. Monte Carlo Methods

5. Temporal Difference Learning