Model Tuning with Reinforcement Learning from Human Advice – Thomas RIEDL
Thomas RIEDL
Master's thesis
Model Tuning with Reinforcement Learning from Human Advice
Abstract:
In this thesis, the concept of reinforcement learning from human advice is applied to the task of model tuning. The overall objective is to integrate evaluative feedback into the training process of reinforcement learning to fine-tune a Multi-Layer-Perceptron model according to specific stakeholder requirements. The concept is especially effective for natural, unconstrained requirements, which are …more
Language used: English
Date on which the thesis was submitted / produced: 8. 2. 2024
Thesis defence
- Supervisor: prof. Dr. Patrick Glauner
Citation record
ISO 690-compliant citation record:
RIEDL, Thomas. \textit{Model Tuning with Reinforcement Learning from Human Advice}. Online. Master's thesis. České Budějovice: University of South Bohemia in České Budějovice, Faculty of Science. 2024. Available from: https://theses.cz/id/foxaof/.
The right form of listing the thesis as a source quoted
RIEDL, Thomas. Model Tuning with Reinforcement Learning from Human Advice. České Budějovice, 2024. diplomová práce (Mgr.). JIHOČESKÁ UNIVERZITA V ČESKÝCH BUDĚJOVICÍCH. Přírodovědecká fakulta
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- Soubory jsou nedostupné do 8. 2. 2027
- Po tomto datu bude práce dostupná: světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: JIHOČESKÁ UNIVERZITA V ČESKÝCH BUDĚJOVICÍCH, Přírodovědecká fakultaUNIVERSITY OF SOUTH BOHEMIA IN ČESKÉ BUDĚJOVICE
Faculty of ScienceMaster programme / field:
Artificial Intelligence and Data Science / Artificial Intelligence and Data Science
Theses on a related topic
- No theses on a related topic available.