SubjectsSubjects(version: 996)
Course, academic year 2026/2027
   
Deep Reinforcement Learning - NPFL139
Title: Hluboké zpětnovazební učení
Form of teaching: lecture+practicals
Guaranteed by: Institute of Formal and Applied Linguistics (32-UFAL)
Faculty: Faculty of Mathematics and Physics
Actual: from 2023
Duration in semesters: 1
Semester: summer
E-Credits: 8
Hours per week, examination: summer s.:3/4, C+Ex [HT]
Capacity: unlimited
Maximum number of enrolled students: unlimited
Min. number of students: unlimited
4EU+: no
Virtual mobility / capacity: no
State of the course: taught
Language: Czech, English
Teaching methods: full-time
Additional information: http://ufal.mff.cuni.cz/courses/npfl139
Repeated enrollment: 2 / 2 / 2 / 2
Guarantor: RNDr. Milan Straka, Ph.D.
Class: Informatika Mgr. - Matematická lingvistika
Classification: Informatics > Computer and Formal Linguistics
Incompatibility : NPFL122
Interchangeability : NPFL122
Is incompatible with: NPFL122
Is interchangeable with: NPFL122
Annotation -
In recent years, reinforcement learning has been combined with deep neural networks, giving rise to game agents with super-human performance (for example for Go or chess, capable of being trained solely by self-play), datacenter cooling algorithms more efficient than human operators, or faster code for sorting or matrix multiplication. The goal of the course is to introduce reinforcement learning employing deep neural networks, focusing both on the theory and on practical implementations. The course is part of the inter-university programme prg.ai Minor (https://prg.ai/minor).
Last update: Mírovský Jiří, RNDr., Ph.D. (16.03.2024)
Aim of the course -

The goal of the course is to introduce reinforcement learning combined with deep neural networks. The course will focus both on theory as well as on practical aspects.

Last update: Mírovský Jiří, RNDr., Ph.D. (11.05.2023)
Course completion requirements -

Students pass the practicals by scoring at least 2/3 of the points from assignments. The assignments are announced regularly throughout the semester and are due within a few weeks. Passing the practicals is not a requirement for taking the exam.

Last update: Straka Milan, RNDr., Ph.D. (31.07.2026)
Literature -
  • Richard S. Sutton and Andrew G. Barto: Reinforcement Learning: An Introduction, Second edition, 2018.
  • David Silver et al.: Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm https://arxiv.org/abs/1712.01815
  • Julian Schrittwieser et al.: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://arxiv.org/abs/1911.08265
Last update: Mírovský Jiří, RNDr., Ph.D. (11.05.2023)
Course assessment methods and requirements for successful completion, grading scheme -

The exam is written and consists of questions randomly chosen from a publicly known list. The requirements of the exam correspond to the course syllabus, in the level of detail which was presented on the lectures.

Last update: Mírovský Jiří, RNDr., Ph.D. (11.05.2023)
Syllabus -

Reinforcement learning framework

Tabular methods

  • Dynamic programming
  • Monte Carlo methods
  • Temporal-difference methods
  • N-step bootstrapping

Functional Approximation

Deep Q networks

  • Rainbow architecture
  • Distributional RL

Policy gradient methods

  • REINFORCE
  • REINFORCE with baseline
  • Actor-critic
  • Proximal Policy Optimization

Continuous action domain

  • Deep Deterministic policy gradient
  • Twin Delayed Deep Deterministic policy gradient
  • Soft Actor Critic

Monte Carlo tree search

  • AlphaZero architecture

Model-based algorithms

  • MCTS with a learned model
  • World models

Discrete latent variable optimization

Introduction to multiagent RL

Last update: Straka Milan, RNDr., Ph.D. (07.05.2025)
Course registration requirements -

Python programming skills and basic PyTorch/Tensorflow skills are required (the latter can be obtained on the Deep Learning NPFL138 course). No previous knowledge of reinforcement learning is necessary.

Last update: Straka Milan, RNDr., Ph.D. (09.11.2023)
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html