Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization
Deep neural networks (DNNs) can be useful within the marine robotics field, but their utility value is restricted by their black-box nature. Explainable artificial intelligence methods attempt to understand how such black-boxes make their decisions. In this work, linear model trees (LMTs) are used t...
Guardado en:
Autores principales: | Vilde B. Gjærum, Inga Strümke, Ole Andreas Alsos, Anastasios M. Lekkas |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/1cef3c3316ff413abd15bb5f091ca66f |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Human-Centered Explainable Artificial Intelligence for Marine Autonomous Surface Vehicles
por: Erik Veitch, et al.
Publicado: (2021) -
A Coordination System between Decision Making and Controlling for Autonomous Collision Avoidance of Large Intelligent Ships
por: Zhengyu Zhou, et al.
Publicado: (2021) -
A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet
por: Dangli Wang, et al.
Publicado: (2021) -
Sea Surface Temperature: From Observation to Applications
por: Francisco Pastor
Publicado: (2021) -
Evaluation of Boulder Deposits Linked to Late Neogene Hurricane Events
por: Markes E. Johnson, et al.
Publicado: (2021)