Institutional Repository of Vilnius University
Tikslinės strategijos skatinamojo mokymosi metodų tyrimas bendravimui su autizmo spektro sutrikimą turinčiais vaikais /
Abstract
dc:descriptionIn this paper, the possibilities of digitizing the Picture Exchange Communication System (PECS) using reinforcement learning methods and the FOX optimization algorithm are investigated. The paper analyzes Q-family algorithms, including Q-learning, Q(λ)-learning, and Double Q-learning, as well as their learning and operational characteristics. During the research, modified FrozenLake experimental environments were developed with adapted reinforcement learning algorithms and PECS card selection logic. The FOX algorithm was applied to optimize the performance of the algorithms by selecting learning parameters. Experimental results demonstrated that FOX optimization improves the performance of reinforcement learning algorithms and stabilizes the obtained results. The results also showed that reinforcement learning methods combined with FOX optimization can be effectively applied to the task of PECS card digitization.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Tomaševskytė, Austėja,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308338193&prefLang=en_US