Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks

Reinforcement learning (RL) provides a unique framework for addressing sequential decision-making problems. Despite the numerous software frameworks proposed to accelerate the development of new algorithms and applications, RL researchers and practitioners often still rely on custom code. This thesi...

Descripción completa

Detalles Bibliográficos
Autor: Bou Hernández, Albert
Tipo de recurso: tesis doctoral
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:CBUC, CESCA
Repositorio:TDR. Tesis Doctorales en Red
OAI Identifier:oai:www.tdx.cat:10803/694233
Acceso en línea:http://hdl.handle.net/10803/694233
Access Level:acceso embargado
Palabra clave:Deep reinforcement learning
Decision-making algorithms
Python libraries
PyTorch
TorchRL
Drug design
62
id ES_2bfb5a9254ec49ea4bd7adbdf878c855
oai_identifier_str oai:www.tdx.cat:10803/694233
network_acronym_str ES
network_name_str España
repository_id_str
spelling Modular approaches and applications in reinforcement learning development and validation of next-generation frameworksBou Hernández, AlbertDeep reinforcement learningDecision-making algorithmsPython librariesPyTorchTorchRLDrug design62Reinforcement learning (RL) provides a unique framework for addressing sequential decision-making problems. Despite the numerous software frameworks proposed to accelerate the development of new algorithms and applications, RL researchers and practitioners often still rely on custom code. This thesis identifies and addresses some core issues contributing to this trend. In the first part, we propose a modular approach for defining distributed RL schemes using basic, reusable building blocks. In the second part, we contribute to the creation of TorchRL, the official PyTorch domain library for general decision-making. TorchRL is designed to be efficient, scalable, and broadly applicable. Finally, we leverage and validate TorchRL by developing ACEGEN, a library for language-based generative drug discovery, and use it to explore new solutions in this field.Programa de Doctorat en Tecnologies de la Informació i les ComunicacionsUniversitat Pompeu FabraDe Fabritiis, GianniUniversitat Pompeu Fabra. Departament de Tecnologies de la Informació i les Comunicacions202520252027info:eu-repo/semantics/doctoralThesisinfo:eu-repo/semantics/publishedVersion134 p.application/pdfhttp://hdl.handle.net/10803/694233TDX (Tesis Doctorals en Xarxa)reponame:TDR. Tesis Doctorales en Redinstname:CBUC, CESCAInglésADVERTIMENT. Tots els drets reservats. L'accés als continguts d'aquesta tesi doctoral i la seva utilització ha de respectar els drets de la persona autora. Pot ser utilitzada per a consulta o estudi personal, així com en activitats o materials d'investigació i docència en els termes establerts a l'art. 32 del Text Refós de la Llei de Propietat Intel·lectual (RDL 1/1996). Per altres utilitzacions es requereix l'autorització prèvia i expressa de la persona autora. En qualsevol cas, en la utilització dels seus continguts caldrà indicar de forma clara el nom i cognoms de la persona autora i el títol de la tesi doctoral. No s'autoritza la seva reproducció o altres formes d'explotació efectuades amb finalitats de lucre ni la seva comunicació pública des d'un lloc aliè al servei TDX. Tampoc s'autoritza la presentació del seu contingut en una finestra o marc aliè a TDX (framing). Aquesta reserva de drets afecta tant als continguts de la tesi com als seus resums i índexs.info:eu-repo/semantics/embargoedAccessoai:www.tdx.cat:10803/6942332026-06-14T12:46:07Z
dc.title.none.fl_str_mv Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
title Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
spellingShingle Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
Bou Hernández, Albert
Deep reinforcement learning
Decision-making algorithms
Python libraries
PyTorch
TorchRL
Drug design
62
title_short Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
title_full Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
title_fullStr Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
title_full_unstemmed Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
title_sort Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks
dc.creator.none.fl_str_mv Bou Hernández, Albert
author Bou Hernández, Albert
author_facet Bou Hernández, Albert
author_role author
dc.contributor.none.fl_str_mv De Fabritiis, Gianni
Universitat Pompeu Fabra. Departament de Tecnologies de la Informació i les Comunicacions
dc.subject.none.fl_str_mv Deep reinforcement learning
Decision-making algorithms
Python libraries
PyTorch
TorchRL
Drug design
62
topic Deep reinforcement learning
Decision-making algorithms
Python libraries
PyTorch
TorchRL
Drug design
62
description Reinforcement learning (RL) provides a unique framework for addressing sequential decision-making problems. Despite the numerous software frameworks proposed to accelerate the development of new algorithms and applications, RL researchers and practitioners often still rely on custom code. This thesis identifies and addresses some core issues contributing to this trend. In the first part, we propose a modular approach for defining distributed RL schemes using basic, reusable building blocks. In the second part, we contribute to the creation of TorchRL, the official PyTorch domain library for general decision-making. TorchRL is designed to be efficient, scalable, and broadly applicable. Finally, we leverage and validate TorchRL by developing ACEGEN, a library for language-based generative drug discovery, and use it to explore new solutions in this field.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025
2027
dc.type.none.fl_str_mv info:eu-repo/semantics/doctoralThesis
info:eu-repo/semantics/publishedVersion
format doctoralThesis
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10803/694233
url http://hdl.handle.net/10803/694233
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/embargoedAccess
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv 134 p.
application/pdf
dc.publisher.none.fl_str_mv Universitat Pompeu Fabra
publisher.none.fl_str_mv Universitat Pompeu Fabra
dc.source.none.fl_str_mv TDX (Tesis Doctorals en Xarxa)
reponame:TDR. Tesis Doctorales en Red
instname:CBUC, CESCA
instname_str CBUC, CESCA
reponame_str TDR. Tesis Doctorales en Red
collection TDR. Tesis Doctorales en Red
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405197818658816
score 15.81155

Similares en LA Referencia