Reinforcement Learning

Data is displayed for the academic year: 2024./2025.

Lecturers

Prof.
Zvonko Kostanjčar
PhD

Course Description

Basic concepts of reinforcement learning. Dynamic programming and Bellman equations. Markov decision processes. The exploration exploitation dilemma. Monte Carlo and bootstrap methods (TD learning). Planning and model-based methods (Dyna algorithm) and model-free methods (Q-learning). Value function and policy approximation. Deep reinforcement learning. Applications of reinforcement learning.

Study Programmes

Postgraduate doctoral study programme

Literature

Richard S. Sutton, Andrew G. Barto (2018.), Reinforcement Learning, A Bradford Book
Csaba Szepesvari (2010.), Algorithms for Reinforcement Learning, Morgan & Claypool Publishers
Mohit Sewak (2019.), Deep Reinforcement Learning, Springer

General

ID 201486
  Summer semester
6 ECTS
L1 English Level