Markov Decision Process and Reinforcement Learning

Topics:

Markov Decision Process (MDP)

Bellman equations

MDP Algorithms: Value & Policy Iteration

Reinforcement Learning

Q-Learning

Tasks:

Read chapters 17 and 21 from the textbook and/or watch the lectures.

Answer the quizzes.

Solve the programming exercise, submit your code, and complete the peer grading.

Assistance for the tasks:

Q&A sessions:

Tuesday, at 15-17.

Join Zoom Meeting: https://tuni.zoom.us/j/69846958622?pwd=VFE2bmtmTEtZY3NaK21HRDJWaStaQT09

Passcode: 276151

Todo

Slides:

Slides: Markov Decision Process

Slides: MDP Algorithms & Bellman Equations

Slides: Reinforcement Learning

Tasks:

Quiz: Markov Decision Process

Quiz: Reinforcement Learning

Quiz: Three state MDP

Posting submission...