{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308337005"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308337005","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Skatinamojo mokymosi modelių tyrimas alternatyviai ir augmentinei komunikacijai /","abstract":"Conventional PECS card selection systems rely on &#64257;xed rules and do not adapt to individual children’s needs or to the stochastic behaviour typical of real therapy settings. The aim of this thesis is to identify the most e&#64256;ective combination of a reinforcement learning algorithm and card selection strategy for improving the e&#64256;ectiveness of augmentative and alternative communication using PECS cards. The results show that the PECS card selection strategy is the dominant factor in AAC system e&#64256;ectiveness, outweighing the choice of reinforcement learning algorithm, and that a stochastic child model reveals essential behavioural di&#64256;erences not visible with a deterministic one. Under the conditions of the noisy virtual child pro&#64257;le, similarity heuristics acquire a decisive role: unreliable feedback destabilises learning, while the semantic similarity component helps to compensate for this e&#64256;ect and maintain the e&#64256;ectiveness of the reinforcement learning model.","abstract_html":"Conventional PECS card selection systems rely on &amp;#64257;xed rules and do not adapt to individual children’s needs or to the stochastic behaviour typical of real therapy settings. The aim of this thesis is to identify the most e&amp;#64256;ective combination of a reinforcement learning algorithm and card selection strategy for improving the e&amp;#64256;ectiveness of augmentative and alternative communication using PECS cards. The results show that the PECS card selection strategy is the dominant factor in AAC system e&amp;#64256;ectiveness, outweighing the choice of reinforcement learning algorithm, and that a stochastic child model reveals essential behavioural di&amp;#64256;erences not visible with a deterministic one. Under the conditions of the noisy virtual child pro&amp;#64257;le, similarity heuristics acquire a decisive role: unreliable feedback destabilises learning, while the semantic similarity component helps to compensate for this e&amp;#64256;ect and maintain the e&amp;#64256;ectiveness of the reinforcement learning model.","abstract_has_math":false,"creators":["Ivanauskaitė, Paulina,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:59Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308337005&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308337005&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308337005","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Ivanauskaitė, Paulina,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308337005/308337005.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308337005&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Conventional PECS card selection systems rely on &#64257;xed rules and do not adapt to individual children’s needs or to the stochastic behaviour typical of real therapy settings. The aim of this thesis is to identify the most e&#64256;ective combination of a reinforcement learning algorithm and card selection strategy for improving the e&#64256;ectiveness of augmentative and alternative communication using PECS cards. The results show that the PECS card selection strategy is the dominant factor in AAC system e&#64256;ectiveness, outweighing the choice of reinforcement learning algorithm, and that a stochastic child model reveals essential behavioural di&#64256;erences not visible with a deterministic one. Under the conditions of the noisy virtual child pro&#64257;le, similarity heuristics acquire a decisive role: unreliable feedback destabilises learning, while the semantic similarity component helps to compensate for this e&#64256;ect and maintain the e&#64256;ectiveness of the reinforcement learning model."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Skatinamojo mokymosi modelių tyrimas alternatyviai ir augmentinei komunikacijai /","Research on reinforcement learning models for alternative and augmentative communication."]}]}],"canonical_facts":{"dc:creator":["Ivanauskaitė, Paulina,"],"dc:date":["2026"],"dc:description":["Conventional PECS card selection systems rely on &#64257;xed rules and do not adapt to individual children’s needs or to the stochastic behaviour typical of real therapy settings. The aim of this thesis is to identify the most e&#64256;ective combination of a reinforcement learning algorithm and card selection strategy for improving the e&#64256;ectiveness of augmentative and alternative communication using PECS cards. The results show that the PECS card selection strategy is the dominant factor in AAC system e&#64256;ectiveness, outweighing the choice of reinforcement learning algorithm, and that a stochastic child model reveals essential behavioural di&#64256;erences not visible with a deterministic one. Under the conditions of the noisy virtual child pro&#64257;le, similarity heuristics acquire a decisive role: unreliable feedback destabilises learning, while the semantic similarity component helps to compensate for this e&#64256;ect and maintain the e&#64256;ectiveness of the reinforcement learning model."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308337005&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308337005/308337005.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Skatinamojo mokymosi modelių tyrimas alternatyviai ir augmentinei komunikacijai /","Research on reinforcement learning models for alternative and augmentative communication."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:59Z"}