SubjectsSubjects(version: 908)
Course, academic year 2022/2023
   Login via CAS
Deep Reinforcement Learning - NPFL122
Title: Hluboké zpětnovazební učení
Guaranteed by: Institute of Formal and Applied Linguistics (32-UFAL)
Faculty: Faculty of Mathematics and Physics
Actual: from 2020
Semester: winter
E-Credits: 5
Hours per week, examination: winter s.:2/2, C+Ex [HT]
Capacity: unlimited
Min. number of students: unlimited
Virtual mobility / capacity: no
State of the course: taught
Language: Czech, English
Teaching methods: full-time
Additional information: http://ufal.mff.cuni.cz/courses/npfl122
Guarantor: RNDr. Milan Straka, Ph.D.
Annotation -
Last update: doc. Mgr. Barbora Vidová Hladká, Ph.D. (25.01.2019)
In recent years, reinforcement learning has been combined with deep neural networks, giving rise to agents with super-human performance (for example for Chess, Go, Dota2, or StarcraftII, capable of being trained solely by self-play), datacenter cooling algorithms being 50% more efficient than trained human operators, or improved machine translation. The goal of the course is to introduce reinforcement learning employing deep neural networks, focusing both on the theory and on practical implementations.
Aim of the course -
Last update: doc. RNDr. Vladislav Kuboň, Ph.D. (05.06.2018)

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.

Course completion requirements -
Last update: doc. RNDr. Vladislav Kuboň, Ph.D. (05.06.2018)

Students pass the practicals by submitting sufficient number of assignments. The assignments are announced regularly the whole semester and are due in several weeks. Considering the rules for completing the practicals, it is not possible to retry passing it. Passing the practicals is not a requirement for going to the exam.

Literature -
Last update: RNDr. Milan Straka, Ph.D. (10.05.2022)
  • 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
Requirements to the exam -
Last update: RNDr. Milan Straka, Ph.D. (15.06.2020)

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.

Syllabus -
Last update: RNDr. Milan Straka, Ph.D. (10.05.2020)

Reinforcement learning framework

Tabular methods

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

Functional Approximation

Deep Q networks

Policy gradient methods

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

Continuous action domain

  • Deep Deterministic policy gradient
  • Twin Delayed Deep Deterministic policy gradient

Monte Carlo tree search

  • AlphaZero architecture

Model-based algorithms

  • MCTS with a learned model

Partially observable environments

Discrete variable optimization

Entry requirements -
Last update: doc. RNDr. Vladislav Kuboň, Ph.D. (05.06.2018)

Python programming skills and Tensorflow skills (or any other deep learning framework) are required, to the extent of the NPFL114 course. No previous knowledge of reinforcement learning is necessary.

 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html