Reinforcement Learning

An introductory course on Reinforcement Learning, structured as four lectures, each followed by a tutorial.

Lectures

Lecture 1: Introduction and MDPs open ↗

Lecture 2: Dynamic Programming open ↗

Lecture 3: Model-Free Prediction open ↗

Lecture 4: Model-Free Control & Deep RL Applications open ↗

Session 1: Markov decision processes, return, value functions, Bellman equations.
Session 2: policy evaluation, policy iteration, value iteration.
Session 3: Monte-Carlo methods, temporal differences TD(0).
Session 4: Monte-Carlo control, SARSA, Q-learning, and a look at deep RL.

Written exercises

Exercises: Introduction and MDPs open ↗

Exercises: Dynamic Programming open ↗

Exercise sheets for sessions 3 and 4, and the notebook tutorials, are in preparation.

See also the Deep Reinforcement Learning training I delivered in companies: same fundamentals, geared towards hands-on practice with Stable-Baselines3 and Gym.

Robotics elective 1 January 0001 →