Skip to main content
Ctrl+K
Introduction to reinforcement learning and control  documentation - Home Introduction to reinforcement learning and control  documentation - Home
  • Github exercise code repository
  • Python support - Discord channel invitation
  • DTU Python Support
  • Gymnasium reinformcement learning library
  • Information
    • About this course
    • Installation
    • Using VS Code
    • Pre-requisites
    • Frequently Asked Questions
  • Exercises
    • Exercise 0: Installation and self-test
    • Exercise 1: The finite-horizon decision problem
    • Exercise 2: Dynamical Programming
    • Exercise 3: DP reformulations and introduction to Control
    • Exercise 4: Discretization and PID control
    • Exercise 5: Linear-quadratic problems in control
    • Exercise 6: Linearization and iterative LQR
    • Exercise 7: Exploration and Bandits
    • Exercise 8: Bellmans equations and exact planning
    • Exercise 9: Monte-carlo methods
    • Exercise 10: Model-Free Control with tabular methods
    • Exercise 11: Linear methods and n-step estimation
    • Exercise 12: Eligibility traces
    • Exercise 13: Deep-Q learning
  • Projects
    • Project 1: Dynamical Programming
    • Project 2: Control theory
    • Project 3: Reinforcement Learning 1
    • Project 4: Reinforcement Learning 2
  • Examples
    • The Pacman Game
    • Control models
    • Week 1: The Pacman game
    • Week 1: The Inventory-control game
    • Week 2: Optimal planning in the Inventory-environment
    • Week 2: Optimal planning with Pacman
    • Week 3: Frozen lake and dynamical programming
    • Week 3: Harmonic Oscillator
    • Week 3: Pendulum with random actions
    • Week 4: PID Control
    • Week 8: Simple bandit
    • Week 8: UCB bandit algorithm
    • Week 9: Policy evaluation
    • Week 9: Policy iteration
    • Week 9: Value iteration
    • Week 10: MC Control
    • Week 10: TD-learning
    • Week 10: MC value estimation
    • Week 11: Sarsa
    • Week 11: Q-learning
    • Week 11: N-step sarsa
    • Week 11: Mountain-car with linear feature approximators
    • Week 12: TD(Lambda)
    • Week 12: Sarsa(Lambda)
    • Week 13: DynaQ
  • Exam practicals
  • .rst

Information

Information#

This section contains general information about the course.

Exercises

  • About this course
    • What you learn
      • Intended Audience
  • Installation
    • Step 1: If you already have conda and VS Code
    • Step 2: Install miniconda and VS Code
    • Step 3: Download the exercises
    • Step 5: Open VS Code
    • Step 6: Install the course software
    • Making sure your files are up to date
    • Known Issues
      • Problem with numpy core
      • Cannot find file
      • Windows
      • Linux: If the right-click menu looks bad
    • Appendix A: Setting up Pycharm
      • In case Pycharm runs your tests twice (and first time fails)
    • Appendix B: Python 3.14
    • Appendix C: If you are taking the course again
    • Appendix D: Install the course software without using Conda
  • Using VS Code
    • Buttons, buttons everywhere
      • Running commands in the terminal
      • Starting the Python shell
      • Running a Python file from the terminal
  • Pre-requisites
    • Programming
    • Linear algebra
    • Analysis
    • Probability theory
  • Frequently Asked Questions
    • Exam
    • Projects
    • ChatGPT and other AI tools
    • General

previous

Introduction to reinforcement learning and control theory

next

About this course

By Tue Herlau

© Copyright 2026.