Evolutionary Optimization of Decision Trees for Interpretable Reinforcement Learning

Created by W.Langdon from gp-bibliography.bib Revision:1.8620

@PhdThesis{Custode:thesis,

• author = "Leonardo Lucio Custode",
• title = "Evolutionary Optimization of Decision Trees for Interpretable Reinforcement Learning",
• school = "Department of Information Engineering and Computer Science, Universita degli Studi di Trento",
• year = "2023",
• address = "Italy",
• month = "27 " # apr,
• keywords = "genetic algorithms, genetic programming, Interpretable AI, XAI, Reinforcement Learning, Evolutionary Computation, UMDA",
• URL = "https://iris.unitn.it/handle/11572/375447",
• URL = "https://iris.unitn.it/retrieve/bafe6bda-8244-42c6-8fff-6a98994cc61b/phd_unitn_leonardolucio_custode.pdf",
• DOI = "10.15168/11572_375447",
• size = "173 pages",
• abstract = "While Artificial Intelligence (AI) is making giant steps, it is also raising concerns about its trustworthiness, due to the fact that widely-used black-box models cannot be exactly understood by humans. One of the ways to improve humans trust towards AI is to use interpretable AI models, i.e., models that can be thoroughly understood by humans, and thus trusted. However, interpretable AI models are not typically used in practice, as they are thought to be less performing than blackbox models. This is more evident in Reinforcement Learning, where relatively little work addresses the problem of performing Reinforcement Learning with interpretable models. we address this gap, proposing methods for Interpretable Reinforcement Learning. For this purpose, we optimize Decision Trees by combining Reinforcement Learning with Evolutionary Computation techniques, which allows us to overcome some of the challenges tied to optimizing Decision Trees in Reinforcement Learning scenarios. The experimental results show that these approaches are competitive with the state-of-the-art score while being extremely easier to interpret. Finally, we show the practical importance of Interpretable AI by digging into the inner working of the solutions obtained.",
• notes = "Defended on 27-apr-2023 In English.

  p111 7.2 'Neuro-Symbolic Analysis of COVID-19 Patients Data'

  Supervisor: Giovanni Iacca",

}

Genetic Programming entries for Leonardo Lucio Custode

Citations