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

Bou Hernández, Albert

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

Document Type

Doctoral thesis
Published Version

Author

Bou Hernández, Albert

Director

De Fabritiis, Gianni

Publication Date

2025-01-27

Pages

134 p.

Embargo date

2027-01-27T01:00:00Z

Citation

Bou Hernández, A. Modular approaches and applications in reinforcement learning development and validation of next-generation frameworks. Universitat Pompeu Fabra; 2025. handle: http://hdl.handle.net/10803/694233

This citation was generated automatically.

Doctoral program

Programa de Doctorat en Tecnologies de la Informació i les Comunicacions

Abstract

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.