Institutional Repository of Vilnius University
Reinforcment learning from human feedback /
Abstract
dc:descriptionThis thesis delves into the exploration of reinforcement learning from human feedback as a solution for general reinforcement learning problems. After a thorough review of the relevant literature, the study compares two distinct reinforcement learning methodologies: traditional reinforcement learning and a variant of reinforcement learning that integrates human feedback loops to enhance the agent’s learning speed by utilizing human feedback. The findings reveal that while our implementation of the reinforcement learning from human feedback algorithm provides a significant edge in training speed, it also introduces additional challenges, such as complex code requirements and prolonged training duration.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Budrys, Dalius,
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- eng
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD192845185&prefLang=en_US