RobertMcCarthy97/tutorials2023

[M2L2023] Tutorial 4: Reinforcement Learning

Authors: Ksenia Konyushkova based on Deep Learning Indaba and DeepMind Educational Resources.

---

Practical 1: Environment, agent and tabular value-based RL

Outline

Introduction to RL with tabular Q learning.

Notebooks

Tutorial:

Solution:

---

Practical 2: Deep RL with Policy Gradient methods.

Policy gradient RL, REINFORCE.

Notebook

Tutorial:

Solution:

---

Practical 3: Deep Q-learning (DQN)

Deep Q-learning.

Notebook

Tutorial:

Solution:

---

Bonus Part

Reinforcement Learning using a Framework.

Notebook

Tutorial: []

---

Note: Designed for education purposes. Please do not distribute without permission.
Questions: Please contact us on the Slack workspace of the M2L school.