Addressing the need for explainable Machine Learning has emerged as one of the most important research directions in modern Artificial Intelligence (AI). While the current dominant paradigm in the field is based on black-box models, typically in the form of (deep) neural networks, these models lack direct interpretability for human users, i.e., their outcomes (and, even more so, their inner working) are opaque and hard to understand. This is hindering the adoption of AI in safety-critical applications, where high interests are at stake. In these applications, explainable by design models, such as decision trees, may be more suitable, as they provide interpretability. Recent works have proposed the hybridization of decision trees and Reinforcement Learning, to combine the advantages of the two approaches. So far, however, these works have focused on the optimization of those hybrid models. Here, we apply MAP-Elites for diversifying hybrid models over a feature space that captures both the model complexity and its behavioral variability. We apply our method on two well-known control problems from the OpenAI Gym library, on which we discuss the "illumination" patterns projected by MAP-Elites, comparing its results against existing similar approaches.
Quality Diversity Evolutionary Learning of Decision Trees / Ferigo, Andrea; Custode, Leonardo Lucio; Iacca, Giovanni. - (2023), pp. 425-432. (Intervento presentato al convegno SAC tenutosi a Tallinn, Estonia nel 27th-31st March 2023) [10.1145/3555776.3577591].
Quality Diversity Evolutionary Learning of Decision Trees
Ferigo, Andrea;Custode, Leonardo Lucio;Iacca, Giovanni
2023-01-01
Abstract
Addressing the need for explainable Machine Learning has emerged as one of the most important research directions in modern Artificial Intelligence (AI). While the current dominant paradigm in the field is based on black-box models, typically in the form of (deep) neural networks, these models lack direct interpretability for human users, i.e., their outcomes (and, even more so, their inner working) are opaque and hard to understand. This is hindering the adoption of AI in safety-critical applications, where high interests are at stake. In these applications, explainable by design models, such as decision trees, may be more suitable, as they provide interpretability. Recent works have proposed the hybridization of decision trees and Reinforcement Learning, to combine the advantages of the two approaches. So far, however, these works have focused on the optimization of those hybrid models. Here, we apply MAP-Elites for diversifying hybrid models over a feature space that captures both the model complexity and its behavioral variability. We apply our method on two well-known control problems from the OpenAI Gym library, on which we discuss the "illumination" patterns projected by MAP-Elites, comparing its results against existing similar approaches.File | Dimensione | Formato | |
---|---|---|---|
2208.12758.pdf
accesso aperto
Tipologia:
Pre-print non referato (Non-refereed preprint)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
238.43 kB
Formato
Adobe PDF
|
238.43 kB | Adobe PDF | Visualizza/Apri |
3555776.3577591.pdf
accesso aperto
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.45 MB
Formato
Adobe PDF
|
1.45 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione