General Information

Course Outline

The course is a basic introduction to reinforcement learning, including:

  • Markov Decision Processes
    • Optimal policy
    • Finite Horizon
    • Infinite discounted horizon
  • Planning
    • Value Iteration
    • Policy Iteration
  • Learning
    • Model based
    • Model free
      • Q-learning
      • TD-methods
      • Actor-Critic
  • Multi-Arm Bandits
  • Partially Observable MDP
  • Linear dynamics

The course will include both theory and applied reinforecement learning,
and a special emphasis will be put on algorithms.

Formalities

Location and Hours

Please check the course schedule.

Staff

li.ca.uat|ruosnam#ruosnaM yahsiY .forP (homepage)

Teaching Assistants:

moc.liamg|001kne#inamhcaN ayilE
moc.liamg|kaylopmada#kayloP madA
Feel free to coordinate reception hours with any of us via email.

Grade

Final Grade is made out of:

  • 60% Exam
  • 20% Homeworks
  • 20% Project

As always, one has to pass the exam in order to pass the course.

Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License