Exploiting semantic segmentation to boost reinforcement learning in video game environments
Entidad
UAM. Departamento de Tecnología Electrónica y de las ComunicacionesEditor
SpringerFecha de edición
2022-09-15Cita
10.1007/s11042-022-13695-1
Multimedia Tools and Applications (2022): 1-19
ISSN
1380-7501 (print); 1573-7721 (online)DOI
10.1007/s11042-022-13695-1Financiado por
Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work is part of the preliminary tasks related to the Harvesting Visual Data (HVD) project (PID2021- 125051OB-I00) funded by the Ministerio de Ciencia e Innovacin of the Spanish GovernmentProyecto
Gobierno de España. PID2021-125051OB-I00Versión del editor
https://doi.org/10.1007/s11042-022-13695-1Materias
Semantic segmentation; Reinforcement learning; Domain adaptation; Synthetic data; Electrónica; TelecomunicacionesNota
The version of record of this article, first published in Multimedia Tools and Applications , is available online at Publisher’s website: http://dx.doi.org/10.1007/s11042-022-13695-1Derechos
© The Author(s) 2022Resumen
In this work we explore enhancing performance of reinforcement learning algorithms in
video game environments by feeding it better, more relevant data. For this purpose, we use
semantic segmentation to transform the images that would be used as input for the reinforcement learning algorithm from their original domain to a simplified semantic domain
with just silhouettes and class labels instead of textures and colors, and then we train the
reinforcement learning algorithm with these simplified images. We have conducted different experiments to study multiple aspects: feasibility of our proposal, and potential benefits
to model generalization and transfer learning. Experiments have been performed with the
Super Mario Bros video game as the testing environment. Our results show multiple advantages for this method. First, it proves that using semantic segmentation enables reaching
higher performance than the baseline reinforcement learning algorithm without modifying the actual algorithm, and in fewer episodes; second, it shows noticeable performance
improvements when training on multiple levels at the same time; and finally, it allows to
apply transfer learning for models trained on visually different environments. We conclude
that using semantic segmentation can certainly help reinforcement learning algorithms that
work with visual data, by refining it. Our results also suggest that other computer vision
techniques may also be beneficial for data prepossessing. Models and code will be available
on github upon acceptance
Lista de ficheros
Tamaño
2.682Mb
Formato
PDF
Descripción
Artículo
Google Scholar:Montalvo Rodrigo, Javier
-
García Martín, Álvaro
-
Bescos Cano, Jesús
Lista de colecciones del ítem
Registros relacionados
Mostrando ítems relacionados por título, autor, creador y materia.
-
Semantic Segmentation in 2D Videogames
Montalvo Rodrigo, Javier
2021-06