ČIEF, M. Off-policy vyhodnocovanie a učenie v adaptívnych systémoch [online]. Brno: Vysoké učení technické v Brně. Fakulta informačních technologií. 2025.
The submitted dissertation is of high quality and complies with requirements. I recommend that the thesis is accepted for PhD defense and the author is awarded the PhD degree.
The conclusion should contain an explicit statement saying whether, in your opinion, the thesis and the student´s achievements until now meet the generally accepted requirements for the award of an academic degree (in accordance with Section 47 of Act No. 111/1998 Coll., on higher education institution).* I affirm that, in my opinion, the thesis and the student’s achievements meet the generally accepted requires for the aware of an academic degree. The PhD thesis is well-written and demonstrates a good level of scientific knowledge as well as practical ability to implement and carry out experimentation on real-world machine learning systems. * Short overview of both the Act and corresponding internal BUT regulations is enclosed.
In conclusion, the dissertation constitutes substantial original research with both theoretical rigor and significant practical contributions to the fields of reinforcement learning and recommendation systems. Matej Čief has demonstrated exceptional capabilities in independent research and interdisciplinary collaboration, and I recommend acceptance of this dissertation by the evaluation committee.
eVSKP id 166445